Xerror commited on
Commit
a7e4991
1 Parent(s): 3d3fe90

Upload 90 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +14 -0
  2. XTTS-v2_models/XTTS-v2_C3PO/.gitattributes +37 -0
  3. XTTS-v2_models/XTTS-v2_C3PO/LICENSE.txt +84 -0
  4. XTTS-v2_models/XTTS-v2_C3PO/README.md +112 -0
  5. XTTS-v2_models/XTTS-v2_C3PO/c3po_1.png +0 -0
  6. XTTS-v2_models/XTTS-v2_C3PO/config.json +158 -0
  7. XTTS-v2_models/XTTS-v2_C3PO/dvae.pth +3 -0
  8. XTTS-v2_models/XTTS-v2_C3PO/hash.md5 +1 -0
  9. XTTS-v2_models/XTTS-v2_C3PO/mel_stats.pth +3 -0
  10. XTTS-v2_models/XTTS-v2_C3PO/model.pth +3 -0
  11. XTTS-v2_models/XTTS-v2_C3PO/reference.wav +3 -0
  12. XTTS-v2_models/XTTS-v2_C3PO/reference2.mp3 +0 -0
  13. XTTS-v2_models/XTTS-v2_C3PO/sample_c3po_generated.wav +0 -0
  14. XTTS-v2_models/XTTS-v2_C3PO/speakers_xtts.pth +3 -0
  15. XTTS-v2_models/XTTS-v2_C3PO/vocab.json +0 -0
  16. XTTS-v2_models/XTTS-v2_PeterJarvis/.gitattributes +37 -0
  17. XTTS-v2_models/XTTS-v2_PeterJarvis/.gitignore +2 -0
  18. XTTS-v2_models/XTTS-v2_PeterJarvis/LICENSE.txt +84 -0
  19. XTTS-v2_models/XTTS-v2_PeterJarvis/README.md +104 -0
  20. XTTS-v2_models/XTTS-v2_PeterJarvis/config.json +158 -0
  21. XTTS-v2_models/XTTS-v2_PeterJarvis/fromtts.wav +3 -0
  22. XTTS-v2_models/XTTS-v2_PeterJarvis/model.pth +3 -0
  23. XTTS-v2_models/XTTS-v2_PeterJarvis/peterdrury.jpg +0 -0
  24. XTTS-v2_models/XTTS-v2_PeterJarvis/reference copy.wav +3 -0
  25. XTTS-v2_models/XTTS-v2_PeterJarvis/reference.wav +3 -0
  26. XTTS-v2_models/XTTS-v2_PeterJarvis/speakers_xtts.pth +3 -0
  27. XTTS-v2_models/XTTS-v2_PeterJarvis/vocab.json +0 -0
  28. XTTS-v2_models/XTTS-v2_S_Dogg/.gitattributes +35 -0
  29. XTTS-v2_models/XTTS-v2_S_Dogg/README.md +5 -0
  30. XTTS-v2_models/XTTS-v2_S_Dogg/config.json +158 -0
  31. XTTS-v2_models/XTTS-v2_S_Dogg/model.pth +3 -0
  32. XTTS-v2_models/XTTS-v2_S_Dogg/reference.wav +0 -0
  33. XTTS-v2_models/XTTS-v2_S_Dogg/speakers_xtts.pth +3 -0
  34. XTTS-v2_models/XTTS-v2_S_Dogg/vocab.json +0 -0
  35. XTTS-v2_models/XTTS-v2_SamuelL/.gitattributes +36 -0
  36. XTTS-v2_models/XTTS-v2_SamuelL/README.md +5 -0
  37. XTTS-v2_models/XTTS-v2_SamuelL/config.json +158 -0
  38. XTTS-v2_models/XTTS-v2_SamuelL/model.pth +3 -0
  39. XTTS-v2_models/XTTS-v2_SamuelL/speakers_xtts.pth +3 -0
  40. XTTS-v2_models/XTTS-v2_SamuelL/vocab.json +0 -0
  41. XTTS-v2_models/XTTS-v2_Yuki-Chan/.gitattributes +40 -0
  42. XTTS-v2_models/XTTS-v2_Yuki-Chan/LICENSE +0 -0
  43. XTTS-v2_models/XTTS-v2_Yuki-Chan/LICENSE.txt +84 -0
  44. XTTS-v2_models/XTTS-v2_Yuki-Chan/README.md +106 -0
  45. XTTS-v2_models/XTTS-v2_Yuki-Chan/carli_avatar_head.png +0 -0
  46. XTTS-v2_models/XTTS-v2_Yuki-Chan/config.json +158 -0
  47. XTTS-v2_models/XTTS-v2_Yuki-Chan/dvae.pth +3 -0
  48. XTTS-v2_models/XTTS-v2_Yuki-Chan/hash.md5 +1 -0
  49. XTTS-v2_models/XTTS-v2_Yuki-Chan/mel_stats.pth +3 -0
  50. XTTS-v2_models/XTTS-v2_Yuki-Chan/model.pth +3 -0
.gitattributes CHANGED
@@ -33,3 +33,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ voices/voice_pain/pain1.wav filter=lfs diff=lfs merge=lfs -text
37
+ voices/voice_pain/pain10.wav filter=lfs diff=lfs merge=lfs -text
38
+ voices/voice_pain/pain11.wav filter=lfs diff=lfs merge=lfs -text
39
+ voices/voice_pain/pain12.wav filter=lfs diff=lfs merge=lfs -text
40
+ voices/voice_pain/pain3.wav filter=lfs diff=lfs merge=lfs -text
41
+ voices/voice_pain/pain4.wav filter=lfs diff=lfs merge=lfs -text
42
+ voices/voice_pain/pain8.wav filter=lfs diff=lfs merge=lfs -text
43
+ voices/voice_pain/pain9.wav filter=lfs diff=lfs merge=lfs -text
44
+ voices/voice_SamuelL/reference.wav filter=lfs diff=lfs merge=lfs -text
45
+ XTTS-v2_models/XTTS-v2_C3PO/reference.wav filter=lfs diff=lfs merge=lfs -text
46
+ XTTS-v2_models/XTTS-v2_PeterJarvis/fromtts.wav filter=lfs diff=lfs merge=lfs -text
47
+ XTTS-v2_models/XTTS-v2_PeterJarvis/reference[[:space:]]copy.wav filter=lfs diff=lfs merge=lfs -text
48
+ XTTS-v2_models/XTTS-v2_PeterJarvis/reference.wav filter=lfs diff=lfs merge=lfs -text
49
+ XTTS-v2_models/XTTS-v2_Yuki-Chan/reference.wav filter=lfs diff=lfs merge=lfs -text
XTTS-v2_models/XTTS-v2_C3PO/.gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ C3PO_1_reference.wav filter=lfs diff=lfs merge=lfs -text
37
+ reference.wav filter=lfs diff=lfs merge=lfs -text
XTTS-v2_models/XTTS-v2_C3PO/LICENSE.txt ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Coqui Public Model License 1.0.0
2
+ https://coqui.ai/cpml.txt
3
+
4
+
5
+ This license allows only non-commercial use of a machine learning model and its outputs.
6
+
7
+
8
+ ## Acceptance
9
+
10
+
11
+ In order to get any license under these terms, you must agree to them as both strict obligations and conditions to all your licenses.
12
+
13
+
14
+ ## Licenses
15
+
16
+
17
+ The licensor grants you a copyright license to do everything you might do with the model that would otherwise infringe the licensor's copyright in it, for any non-commercial purpose. The licensor grants you a patent license that covers patent claims the licensor can license, or becomes able to license, that you would infringe by using the model in the form provided by
18
+ the licensor, for any non-commercial purpose.
19
+
20
+
21
+ ## Non-commercial Purpose
22
+
23
+
24
+ Non-commercial purposes include any of the following uses of the model or its output, but only so far as you do not receive any direct or indirect payment arising from the use of the model or its output.
25
+
26
+
27
+ ### Personal use for research, experiment, and testing for the benefit of public knowledge, personal study, private entertainment, hobby projects, amateur pursuits, or religious
28
+ observance.
29
+
30
+
31
+ ### Use by commercial or for-profit entities for testing, evaluation, or non-commercial research and development. Use of the model to train other models for commercial use is not a non-commercial purpose.
32
+
33
+
34
+ ### Use by any charitable organization for charitable purposes, or for testing or evaluation. Use for revenue-generating activity, including projects directly funded by government grants, is not a non-commercial purpose.
35
+
36
+
37
+ ## Notices
38
+
39
+
40
+ You must ensure that anyone who gets a copy of any part of the model, or any modification of the model, or their output, from you also gets a copy of these terms or the URL for them above.
41
+
42
+
43
+ ## No Other Rights
44
+
45
+
46
+ These terms do not allow you to sublicense or transfer any of your licenses to anyone else, or prevent the licensor from granting licenses to anyone else. These terms do not imply
47
+ any other licenses.
48
+
49
+
50
+ ## Patent Defense
51
+
52
+
53
+ If you make any written claim that the model infringes or contributes to infringement of any patent, your licenses for the model granted under these terms ends immediately. If your company makes such a claim, your patent license ends immediately for work on behalf of your company.
54
+
55
+
56
+ ## Violations
57
+
58
+
59
+ The first time you are notified in writing that you have violated any of these terms, or done anything with the model or its output that is not covered by your licenses, your licenses can nonetheless continue if you come into full compliance with these terms, and take practical steps to correct past violations, within 30 days of receiving notice. Otherwise, all your licenses
60
+ end immediately.
61
+
62
+
63
+ ## No Liability
64
+
65
+
66
+ ***As far as the law allows, the model and its output come as is, without any warranty or condition, and the licensor will not be liable to you for any damages arising out of these terms or the use or nature of the model or its output, under any kind of legal claim. If this provision is not enforceable in your jurisdiction, your licenses are void.***
67
+
68
+
69
+ ## Definitions
70
+
71
+
72
+ The **licensor** is the individual or entity offering these terms, and the **model** is the model the licensor makes available under these terms, including any documentation or similar information about the model.
73
+
74
+
75
+ **You** refers to the individual or entity agreeing to these terms.
76
+
77
+
78
+ **Your company** is any legal entity, sole proprietorship, or other kind of organization that you work for, plus all organizations that have control over, are under the control of, or are under common control with that organization. **Control** means ownership of substantially all the assets of an entity, or the power to direct its management and policies by vote, contract, or otherwise. Control can be direct or indirect.
79
+
80
+
81
+ **Your licenses** are all the licenses granted to you under these terms.
82
+
83
+
84
+ **Use** means anything you do with the model or its output requiring one of your licenses.
XTTS-v2_models/XTTS-v2_C3PO/README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: coqui-public-model-license
4
+ license_link: https://coqui.ai/cpml
5
+ library_name: coqui
6
+ pipeline_tag: text-to-speech
7
+ widget:
8
+ - text: "Once when I was six years old I saw a magnificent picture"
9
+ ---
10
+
11
+ # ⓍTTS_v2 - C-3PO Fine-Tuned Voice Model (Borcherding/XTTS-v2_C3PO)
12
+ Artistic Whimsy and Galactic Musings
13
+ The ⓍTTS (Satirical Text-to-Speech) model, residing within the Borcherding/XTTS-v2_C3PO repository, transcends mere technology. It becomes an art piece—an interplay of code, creativity, and humor. Imagine a digital gallery where visitors encounter C-3PO’s satirical musings echoing through the virtual halls.
14
+
15
+ Key Features
16
+ C-3PO’s Quirky Voice: Leveraging 20 unique voice lines sourced from Voicy, the ⓍTTS model captures the essence of C-3PO’s distinctive speech patterns. Expect a delightful blend of protocol droid formality, unexpected commentary, and occasional existential musings.
17
+ Satirical Tone: Rather than adhering to a neutral or serious tone, the ⓍTTS model revels in satire. It playfully exaggerates intonation, injects humorous pauses, and occasionally breaks the fourth wall. Each voice line becomes a brushstroke on the canvas of imagination.
18
+
19
+ This repository hosts a fine-tuned version of the ⓍTTS model, utilizing 20 unique voice lines from C-3PO, the iconic Star Wars character. The voice lines were sourced from [Voicy](https://www.voicy.network/official-soundboards/movies/c3po).
20
+
21
+ ![C-3PO](c3po_1.png)
22
+
23
+ Listen to a sample of the ⓍTTS_v2 - C-3PO Fine-Tuned Model:
24
+
25
+ <audio controls>
26
+ <source src="https://huggingface.co/Borcherding/XTTS-v2_C3PO/raw/main/sample_c3po_generated.wav" type="audio/wav">
27
+ Your browser does not support the audio element.
28
+ </audio>
29
+
30
+ Here's a C-3PO mp3 voice line clip from the training data:
31
+
32
+ <audio controls>
33
+ <source src="https://huggingface.co/Borcherding/XTTS-v2_C3PO/raw/main/reference2.mp3" type="audio/wav">
34
+ Your browser does not support the audio element.
35
+ </audio>
36
+
37
+ ## Features
38
+ - 🎙️ **Voice Cloning**: Realistic voice cloning with just a short audio clip.
39
+ - 🌍 **Multi-Lingual Support**: Generates speech in 17 different languages while maintaining C-3PO's distinct voice.
40
+ - 😃 **Emotion & Style Transfer**: Captures the emotional tone and style of the original voice.
41
+ - 🔄 **Cross-Language Cloning**: Maintains the unique voice characteristics across different languages.
42
+ - 🎧 **High-Quality Audio**: Outputs at a 24kHz sampling rate for clear and high-fidelity audio.
43
+
44
+ ## Supported Languages
45
+ The model supports the following 17 languages: English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt), Polish (pl), Turkish (tr), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (ko), and Hindi (hi).
46
+
47
+ ## Usage in Roll Cage
48
+ 🤖💬 Boost your AI experience with this Ollama add-on! Enjoy real-time audio 🎙️ and text 🔍 chats, LaTeX rendering 📜, agent automations ⚙️, workflows 🔄, text-to-image 📝➡️🖼️, image-to-text 🖼️➡️🔤, image-to-video 🖼️➡️🎥 transformations. Fine-tune text 📝, voice 🗣️, and image 🖼️ gens. Includes Windows macro controls 🖥️ and DuckDuckGo search.
49
+
50
+ [ollama_agent_roll_cage (OARC)](https://github.com/Leoleojames1/ollama_agent_roll_cage) is a completely local Python & CMD toolset add-on for the Ollama command line interface. The OARC toolset automates the creation of agents, giving the user more control over the likely output. It provides SYSTEM prompt templates for each ./Modelfile, allowing users to design and deploy custom agents quickly. Users can select which local model file is used in agent construction with the desired system prompt.
51
+
52
+ ## Why This Model for Roll Cage?
53
+ The C-3PO fine-tuned model was designed for the Roll Cage chatbot to enhance user interaction with a familiar and beloved voice. By incorporating C-3PO's distinctive speech patterns and tone, Roll Cage becomes more engaging and entertaining. The addition of multi-lingual support and emotion transfer ensures that the chatbot can communicate effectively and expressively across different languages and contexts, providing a more immersive experience for users.
54
+
55
+ ## CoquiTTS and Resources
56
+ - 🐸💬 **CoquiTTS**: [Coqui TTS on GitHub](https://github.com/coqui-ai/TTS)
57
+ - 📚 **Documentation**: [ReadTheDocs](https://tts.readthedocs.io/en/latest/)
58
+ - 👩‍💻 **Questions**: [GitHub Discussions](https://github.com/coqui-ai/TTS/discussions)
59
+ - 🗯 **Community**: [Discord](https://discord.gg/5eXr5seRrv)
60
+
61
+ ## License
62
+ This model is licensed under the [Coqui Public Model License](https://coqui.ai/cpml). Read more about the origin story of CPML [here](https://coqui.ai/blog/tts/cpml).
63
+
64
+ ## Contact
65
+ Join our 🐸Community on [Discord](https://discord.gg/fBC58unbKE) and follow us on [Twitter](https://twitter.com/coqui_ai). For inquiries, email us at [email protected].
66
+
67
+ Using 🐸TTS API:
68
+
69
+ ```python
70
+ from TTS.api import TTS
71
+
72
+ tts = TTS(model_path="D:/CodingGit_StorageHDD/Ollama_Custom_Mods/ollama_agent_roll_cage/AgentFiles/Ignored_TTS/XTTS-v2_C3PO/",
73
+ config_path="D:/CodingGit_StorageHDD/Ollama_Custom_Mods/ollama_agent_roll_cage/AgentFiles/Ignored_TTS/XTTS-v2_C3PO/config.json", progress_bar=False, gpu=True).to(self.device)
74
+
75
+ # generate speech by cloning a voice using default settings
76
+ tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
77
+ file_path="output.wav",
78
+ speaker_wav="/path/to/target/speaker.wav",
79
+ language="en")
80
+
81
+ ```
82
+
83
+ Using 🐸TTS Command line:
84
+
85
+ ```console
86
+ tts --model_name tts_models/multilingual/multi-dataset/xtts_v2 \
87
+ --text "Bugün okula gitmek istemiyorum." \
88
+ --speaker_wav /path/to/target/speaker.wav \
89
+ --language_idx tr \
90
+ --use_cuda true
91
+ ```
92
+
93
+ Using the model directly:
94
+
95
+ ```python
96
+ from TTS.tts.configs.xtts_config import XttsConfig
97
+ from TTS.tts.models.xtts import Xtts
98
+
99
+ config = XttsConfig()
100
+ config.load_json("/path/to/xtts/config.json")
101
+ model = Xtts.init_from_config(config)
102
+ model.load_checkpoint(config, checkpoint_dir="/path/to/xtts/", eval=True)
103
+ model.cuda()
104
+
105
+ outputs = model.synthesize(
106
+ "It took me quite a long time to develop a voice and now that I have it I am not going to be silent.",
107
+ config,
108
+ speaker_wav="/data/TTS-public/_refclips/3.wav",
109
+ gpt_cond_len=3,
110
+ language="en",
111
+ )
112
+ ```
XTTS-v2_models/XTTS-v2_C3PO/c3po_1.png ADDED
XTTS-v2_models/XTTS-v2_C3PO/config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_path": "output",
3
+ "logger_uri": null,
4
+ "run_name": "run",
5
+ "project_name": null,
6
+ "run_description": "\ud83d\udc38Coqui trainer run.",
7
+ "print_step": 25,
8
+ "plot_step": 100,
9
+ "model_param_stats": false,
10
+ "wandb_entity": null,
11
+ "dashboard_logger": "tensorboard",
12
+ "save_on_interrupt": true,
13
+ "log_model_step": null,
14
+ "save_step": 10000,
15
+ "save_n_checkpoints": 5,
16
+ "save_checkpoints": true,
17
+ "save_all_best": false,
18
+ "save_best_after": 10000,
19
+ "target_loss": null,
20
+ "print_eval": false,
21
+ "test_delay_epochs": 0,
22
+ "run_eval": true,
23
+ "run_eval_steps": null,
24
+ "distributed_backend": "nccl",
25
+ "distributed_url": "tcp://localhost:54321",
26
+ "mixed_precision": false,
27
+ "precision": "fp16",
28
+ "epochs": 1000,
29
+ "batch_size": 32,
30
+ "eval_batch_size": 16,
31
+ "grad_clip": 0.0,
32
+ "scheduler_after_epoch": true,
33
+ "lr": 0.001,
34
+ "optimizer": "radam",
35
+ "optimizer_params": null,
36
+ "lr_scheduler": null,
37
+ "lr_scheduler_params": {},
38
+ "use_grad_scaler": false,
39
+ "allow_tf32": false,
40
+ "cudnn_enable": true,
41
+ "cudnn_deterministic": false,
42
+ "cudnn_benchmark": false,
43
+ "training_seed": 54321,
44
+ "model": "xtts",
45
+ "num_loader_workers": 0,
46
+ "num_eval_loader_workers": 0,
47
+ "use_noise_augment": false,
48
+ "audio": {
49
+ "sample_rate": 22050,
50
+ "output_sample_rate": 24000
51
+ },
52
+ "use_phonemes": false,
53
+ "phonemizer": null,
54
+ "phoneme_language": null,
55
+ "compute_input_seq_cache": false,
56
+ "text_cleaner": null,
57
+ "enable_eos_bos_chars": false,
58
+ "test_sentences_file": "",
59
+ "phoneme_cache_path": null,
60
+ "characters": null,
61
+ "add_blank": false,
62
+ "batch_group_size": 0,
63
+ "loss_masking": null,
64
+ "min_audio_len": 1,
65
+ "max_audio_len": Infinity,
66
+ "min_text_len": 1,
67
+ "max_text_len": Infinity,
68
+ "compute_f0": false,
69
+ "compute_energy": false,
70
+ "compute_linear_spec": false,
71
+ "precompute_num_workers": 0,
72
+ "start_by_longest": false,
73
+ "shuffle": false,
74
+ "drop_last": false,
75
+ "datasets": [
76
+ {
77
+ "formatter": "",
78
+ "dataset_name": "",
79
+ "path": "",
80
+ "meta_file_train": "",
81
+ "ignored_speakers": null,
82
+ "language": "",
83
+ "phonemizer": "",
84
+ "meta_file_val": "",
85
+ "meta_file_attn_mask": ""
86
+ }
87
+ ],
88
+ "test_sentences": [],
89
+ "eval_split_max_size": null,
90
+ "eval_split_size": 0.01,
91
+ "use_speaker_weighted_sampler": false,
92
+ "speaker_weighted_sampler_alpha": 1.0,
93
+ "use_language_weighted_sampler": false,
94
+ "language_weighted_sampler_alpha": 1.0,
95
+ "use_length_weighted_sampler": false,
96
+ "length_weighted_sampler_alpha": 1.0,
97
+ "model_args": {
98
+ "gpt_batch_size": 1,
99
+ "enable_redaction": false,
100
+ "kv_cache": true,
101
+ "gpt_checkpoint": null,
102
+ "clvp_checkpoint": null,
103
+ "decoder_checkpoint": null,
104
+ "num_chars": 255,
105
+ "tokenizer_file": "",
106
+ "gpt_max_audio_tokens": 605,
107
+ "gpt_max_text_tokens": 402,
108
+ "gpt_max_prompt_tokens": 70,
109
+ "gpt_layers": 30,
110
+ "gpt_n_model_channels": 1024,
111
+ "gpt_n_heads": 16,
112
+ "gpt_number_text_tokens": 6153,
113
+ "gpt_start_text_token": null,
114
+ "gpt_stop_text_token": null,
115
+ "gpt_num_audio_tokens": 1026,
116
+ "gpt_start_audio_token": 1024,
117
+ "gpt_stop_audio_token": 1025,
118
+ "gpt_code_stride_len": 1024,
119
+ "gpt_use_masking_gt_prompt_approach": true,
120
+ "gpt_use_perceiver_resampler": true,
121
+ "input_sample_rate": 22050,
122
+ "output_sample_rate": 24000,
123
+ "output_hop_length": 256,
124
+ "decoder_input_dim": 1024,
125
+ "d_vector_dim": 512,
126
+ "cond_d_vector_in_each_upsampling_layer": true,
127
+ "duration_const": 102400
128
+ },
129
+ "model_dir": null,
130
+ "languages": [
131
+ "en",
132
+ "es",
133
+ "fr",
134
+ "de",
135
+ "it",
136
+ "pt",
137
+ "pl",
138
+ "tr",
139
+ "ru",
140
+ "nl",
141
+ "cs",
142
+ "ar",
143
+ "zh-cn",
144
+ "hu",
145
+ "ko",
146
+ "ja"
147
+ ],
148
+ "temperature": 0.75,
149
+ "length_penalty": 1.0,
150
+ "repetition_penalty": 10.0,
151
+ "top_k": 50,
152
+ "top_p": 0.85,
153
+ "num_gpt_outputs": 1,
154
+ "gpt_cond_len": 30,
155
+ "gpt_cond_chunk_len": 4,
156
+ "max_ref_len": 30,
157
+ "sound_norm_refs": false
158
+ }
XTTS-v2_models/XTTS-v2_C3PO/dvae.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29bc227d410d4991e0a8c09b858f77415013eeb9fba9650258e96095557d97a
3
+ size 210514388
XTTS-v2_models/XTTS-v2_C3PO/hash.md5 ADDED
@@ -0,0 +1 @@
 
 
1
+ 10f92b55c512af7a8d39d650547a15a7
XTTS-v2_models/XTTS-v2_C3PO/mel_stats.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f69422a8a8f344c4fca2f0c6b8d41d2151d6615b7321e48e6bb15ae949b119c
3
+ size 1067
XTTS-v2_models/XTTS-v2_C3PO/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd1c3c256ee8dd256b9a9294da608b4ff97d35d249e6e07aa50f49d3c2a183b
3
+ size 1863948502
XTTS-v2_models/XTTS-v2_C3PO/reference.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa46f71bf8e9c0a911de4d40b21ebe1298c9354d3dee2f5e0179030eab80f4e1
3
+ size 1920220
XTTS-v2_models/XTTS-v2_C3PO/reference2.mp3 ADDED
Binary file (48.9 kB). View file
 
XTTS-v2_models/XTTS-v2_C3PO/sample_c3po_generated.wav ADDED
Binary file (570 kB). View file
 
XTTS-v2_models/XTTS-v2_C3PO/speakers_xtts.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
3
+ size 7754818
XTTS-v2_models/XTTS-v2_C3PO/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
XTTS-v2_models/XTTS-v2_PeterJarvis/.gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ reference.wav filter=lfs diff=lfs merge=lfs -text
37
+ fromtts.wav filter=lfs diff=lfs merge=lfs -text
XTTS-v2_models/XTTS-v2_PeterJarvis/.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ *
2
+ !.gitignore
XTTS-v2_models/XTTS-v2_PeterJarvis/LICENSE.txt ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Coqui Public Model License 1.0.0
2
+ https://coqui.ai/cpml.txt
3
+
4
+
5
+ This license allows only non-commercial use of a machine learning model and its outputs.
6
+
7
+
8
+ ## Acceptance
9
+
10
+
11
+ In order to get any license under these terms, you must agree to them as both strict obligations and conditions to all your licenses.
12
+
13
+
14
+ ## Licenses
15
+
16
+
17
+ The licensor grants you a copyright license to do everything you might do with the model that would otherwise infringe the licensor's copyright in it, for any non-commercial purpose. The licensor grants you a patent license that covers patent claims the licensor can license, or becomes able to license, that you would infringe by using the model in the form provided by
18
+ the licensor, for any non-commercial purpose.
19
+
20
+
21
+ ## Non-commercial Purpose
22
+
23
+
24
+ Non-commercial purposes include any of the following uses of the model or its output, but only so far as you do not receive any direct or indirect payment arising from the use of the model or its output.
25
+
26
+
27
+ ### Personal use for research, experiment, and testing for the benefit of public knowledge, personal study, private entertainment, hobby projects, amateur pursuits, or religious
28
+ observance.
29
+
30
+
31
+ ### Use by commercial or for-profit entities for testing, evaluation, or non-commercial research and development. Use of the model to train other models for commercial use is not a non-commercial purpose.
32
+
33
+
34
+ ### Use by any charitable organization for charitable purposes, or for testing or evaluation. Use for revenue-generating activity, including projects directly funded by government grants, is not a non-commercial purpose.
35
+
36
+
37
+ ## Notices
38
+
39
+
40
+ You must ensure that anyone who gets a copy of any part of the model, or any modification of the model, or their output, from you also gets a copy of these terms or the URL for them above.
41
+
42
+
43
+ ## No Other Rights
44
+
45
+
46
+ These terms do not allow you to sublicense or transfer any of your licenses to anyone else, or prevent the licensor from granting licenses to anyone else. These terms do not imply
47
+ any other licenses.
48
+
49
+
50
+ ## Patent Defense
51
+
52
+
53
+ If you make any written claim that the model infringes or contributes to infringement of any patent, your licenses for the model granted under these terms ends immediately. If your company makes such a claim, your patent license ends immediately for work on behalf of your company.
54
+
55
+
56
+ ## Violations
57
+
58
+
59
+ The first time you are notified in writing that you have violated any of these terms, or done anything with the model or its output that is not covered by your licenses, your licenses can nonetheless continue if you come into full compliance with these terms, and take practical steps to correct past violations, within 30 days of receiving notice. Otherwise, all your licenses
60
+ end immediately.
61
+
62
+
63
+ ## No Liability
64
+
65
+
66
+ ***As far as the law allows, the model and its output come as is, without any warranty or condition, and the licensor will not be liable to you for any damages arising out of these terms or the use or nature of the model or its output, under any kind of legal claim. If this provision is not enforceable in your jurisdiction, your licenses are void.***
67
+
68
+
69
+ ## Definitions
70
+
71
+
72
+ The **licensor** is the individual or entity offering these terms, and the **model** is the model the licensor makes available under these terms, including any documentation or similar information about the model.
73
+
74
+
75
+ **You** refers to the individual or entity agreeing to these terms.
76
+
77
+
78
+ **Your company** is any legal entity, sole proprietorship, or other kind of organization that you work for, plus all organizations that have control over, are under the control of, or are under common control with that organization. **Control** means ownership of substantially all the assets of an entity, or the power to direct its management and policies by vote, contract, or otherwise. Control can be direct or indirect.
79
+
80
+
81
+ **Your licenses** are all the licenses granted to you under these terms.
82
+
83
+
84
+ **Use** means anything you do with the model or its output requiring one of your licenses.
XTTS-v2_models/XTTS-v2_PeterJarvis/README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: coqui-public-model-license
4
+ license_link: https://coqui.ai/cpml
5
+ library_name: coqui
6
+ pipeline_tag: text-to-speech
7
+ widget:
8
+ - text: "Once when I was six years old I saw a magnificent picture"
9
+ ---
10
+
11
+ # ⓍTTS_v2 - Peter Drury Fine-Tuned Model
12
+
13
+ This repository hosts a fine-tuned version of the ⓍTTS model, utilizing 2.3 minutes of unique voice lines from Peter Drury, The voice lines were sourced from he's podcast with JOE on youtube, can be found here:
14
+ [Peter Drury RANKS His Best Commentary Moments & Reveals Commentary Secrets! MESSI WIN WORLD CUP!](https://www.youtube.com/watch?v=ibT6PINpyaw&t)
15
+
16
+ ![Peter Drury](peterdrury.jpg)
17
+
18
+ Listen to a sample of the ⓍTTS_v2 - Peter Drury Fine-Tuned Model:
19
+
20
+ <audio controls>
21
+ <source src="https://huggingface.co/kodoqmc/XTTS-v2_PeterDrury/resolve/main/fromtts.wav" type="audio/wav">
22
+ Your browser does not support the audio element.
23
+ </audio>
24
+
25
+ Here's a Peter Drury mp3 voice line clip from the training data:
26
+
27
+ <audio controls>
28
+ <source src="https://huggingface.co/kodoqmc/XTTS-v2_PeterDrury/resolve/main/reference.wav" type="audio/wav">
29
+ Your browser does not support the audio element.
30
+ </audio>
31
+
32
+ ## Features
33
+ - 🎙️ **Voice Cloning**: Realistic voice cloning with just a short audio clip.
34
+ - 🌍 **Multi-Lingual Support**: Generates speech in 17 different languages while maintaining Peter Drury's voice.
35
+ - 😃 **Emotion & Style Transfer**: Captures the emotional tone and style of the original voice.
36
+ - 🔄 **Cross-Language Cloning**: Maintains the unique voice characteristics across different languages.
37
+ - 🎧 **High-Quality Audio**: Outputs at a 24kHz sampling rate for clear and high-fidelity audio.
38
+
39
+ ## Supported Languages
40
+ The model supports the following 17 languages: English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt), Polish (pl), Turkish (tr), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (ko), and Hindi (hi).
41
+
42
+ ## Usage in Roll Cage
43
+ 🤖💬 Boost your AI experience with this Ollama add-on! Enjoy real-time audio 🎙️ and text 🔍 chats, LaTeX rendering 📜, agent automations ⚙️, workflows 🔄, text-to-image 📝➡️🖼️, image-to-text 🖼️➡️🔤, image-to-video 🖼️➡️🎥 transformations. Fine-tune text 📝, voice 🗣️, and image 🖼️ gens. Includes Windows macro controls 🖥️ and DuckDuckGo search.
44
+
45
+ [ollama_agent_roll_cage (OARC)](https://github.com/Leoleojames1/ollama_agent_roll_cage) is a completely local Python & CMD toolset add-on for the Ollama command line interface. The OARC toolset automates the creation of agents, giving the user more control over the likely output. It provides SYSTEM prompt templates for each ./Modelfile, allowing users to design and deploy custom agents quickly. Users can select which local model file is used in agent construction with the desired system prompt.
46
+
47
+ ## CoquiTTS and Resources
48
+ - 🐸💬 **CoquiTTS**: [Coqui TTS on GitHub](https://github.com/coqui-ai/TTS)
49
+ - 📚 **Documentation**: [ReadTheDocs](https://tts.readthedocs.io/en/latest/)
50
+ - 👩‍💻 **Questions**: [GitHub Discussions](https://github.com/coqui-ai/TTS/discussions)
51
+ - 🗯 **Community**: [Discord](https://discord.gg/5eXr5seRrv)
52
+
53
+ ## License
54
+ This model is licensed under the [Coqui Public Model License](https://coqui.ai/cpml). Read more about the origin story of CPML [here](https://coqui.ai/blog/tts/cpml).
55
+
56
+ ## Contact
57
+ Join our 🐸Community on [Discord](https://discord.gg/fBC58unbKE) and follow us on [Twitter](https://twitter.com/coqui_ai). For inquiries, email us at [email protected].
58
+
59
+ Using 🐸TTS API:
60
+
61
+ ```python
62
+ from TTS.api import TTS
63
+
64
+ tts = TTS(model_path="D:/AI/ollama_agent_roll_cage/AgentFiles/Ignored_TTS/XTTS-v2_PeterDrury/",
65
+ config_path="D:/AI/ollama_agent_roll_cage/AgentFiles/Ignored_TTS/XTTS-v2_PeterDrury/config.json", progress_bar=False, gpu=True).to(self.device)
66
+
67
+ # generate speech by cloning a voice using default settings
68
+ tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
69
+ file_path="output.wav",
70
+ speaker_wav="/path/to/target/speaker.wav",
71
+ language="en")
72
+
73
+ ```
74
+
75
+ Using 🐸TTS Command line:
76
+
77
+ ```console
78
+ tts --model_name tts_models/multilingual/multi-dataset/xtts_v2 \
79
+ --text "Bugün okula gitmek istemiyorum." \
80
+ --speaker_wav /path/to/target/speaker.wav \
81
+ --language_idx tr \
82
+ --use_cuda true
83
+ ```
84
+
85
+ Using the model directly:
86
+
87
+ ```python
88
+ from TTS.tts.configs.xtts_config import XttsConfig
89
+ from TTS.tts.models.xtts import Xtts
90
+
91
+ config = XttsConfig()
92
+ config.load_json("/path/to/xtts/config.json")
93
+ model = Xtts.init_from_config(config)
94
+ model.load_checkpoint(config, checkpoint_dir="/path/to/xtts/", eval=True)
95
+ model.cuda()
96
+
97
+ outputs = model.synthesize(
98
+ "It took me quite a long time to develop a voice and now that I have it I am not going to be silent.",
99
+ config,
100
+ speaker_wav="/data/TTS-public/_refclips/3.wav",
101
+ gpt_cond_len=3,
102
+ language="en",
103
+ )
104
+ ```
XTTS-v2_models/XTTS-v2_PeterJarvis/config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_path": "output",
3
+ "logger_uri": null,
4
+ "run_name": "run",
5
+ "project_name": null,
6
+ "run_description": "\ud83d\udc38Coqui trainer run.",
7
+ "print_step": 25,
8
+ "plot_step": 100,
9
+ "model_param_stats": false,
10
+ "wandb_entity": null,
11
+ "dashboard_logger": "tensorboard",
12
+ "save_on_interrupt": true,
13
+ "log_model_step": null,
14
+ "save_step": 10000,
15
+ "save_n_checkpoints": 5,
16
+ "save_checkpoints": true,
17
+ "save_all_best": false,
18
+ "save_best_after": 10000,
19
+ "target_loss": null,
20
+ "print_eval": false,
21
+ "test_delay_epochs": 0,
22
+ "run_eval": true,
23
+ "run_eval_steps": null,
24
+ "distributed_backend": "nccl",
25
+ "distributed_url": "tcp://localhost:54321",
26
+ "mixed_precision": false,
27
+ "precision": "fp16",
28
+ "epochs": 1000,
29
+ "batch_size": 32,
30
+ "eval_batch_size": 16,
31
+ "grad_clip": 0.0,
32
+ "scheduler_after_epoch": true,
33
+ "lr": 0.001,
34
+ "optimizer": "radam",
35
+ "optimizer_params": null,
36
+ "lr_scheduler": null,
37
+ "lr_scheduler_params": {},
38
+ "use_grad_scaler": false,
39
+ "allow_tf32": false,
40
+ "cudnn_enable": true,
41
+ "cudnn_deterministic": false,
42
+ "cudnn_benchmark": false,
43
+ "training_seed": 54321,
44
+ "model": "xtts",
45
+ "num_loader_workers": 0,
46
+ "num_eval_loader_workers": 0,
47
+ "use_noise_augment": false,
48
+ "audio": {
49
+ "sample_rate": 22050,
50
+ "output_sample_rate": 24000
51
+ },
52
+ "use_phonemes": false,
53
+ "phonemizer": null,
54
+ "phoneme_language": null,
55
+ "compute_input_seq_cache": false,
56
+ "text_cleaner": null,
57
+ "enable_eos_bos_chars": false,
58
+ "test_sentences_file": "",
59
+ "phoneme_cache_path": null,
60
+ "characters": null,
61
+ "add_blank": false,
62
+ "batch_group_size": 0,
63
+ "loss_masking": null,
64
+ "min_audio_len": 1,
65
+ "max_audio_len": Infinity,
66
+ "min_text_len": 1,
67
+ "max_text_len": Infinity,
68
+ "compute_f0": false,
69
+ "compute_energy": false,
70
+ "compute_linear_spec": false,
71
+ "precompute_num_workers": 0,
72
+ "start_by_longest": false,
73
+ "shuffle": false,
74
+ "drop_last": false,
75
+ "datasets": [
76
+ {
77
+ "formatter": "",
78
+ "dataset_name": "",
79
+ "path": "",
80
+ "meta_file_train": "",
81
+ "ignored_speakers": null,
82
+ "language": "",
83
+ "phonemizer": "",
84
+ "meta_file_val": "",
85
+ "meta_file_attn_mask": ""
86
+ }
87
+ ],
88
+ "test_sentences": [],
89
+ "eval_split_max_size": null,
90
+ "eval_split_size": 0.01,
91
+ "use_speaker_weighted_sampler": false,
92
+ "speaker_weighted_sampler_alpha": 1.0,
93
+ "use_language_weighted_sampler": false,
94
+ "language_weighted_sampler_alpha": 1.0,
95
+ "use_length_weighted_sampler": false,
96
+ "length_weighted_sampler_alpha": 1.0,
97
+ "model_args": {
98
+ "gpt_batch_size": 1,
99
+ "enable_redaction": false,
100
+ "kv_cache": true,
101
+ "gpt_checkpoint": null,
102
+ "clvp_checkpoint": null,
103
+ "decoder_checkpoint": null,
104
+ "num_chars": 255,
105
+ "tokenizer_file": "",
106
+ "gpt_max_audio_tokens": 605,
107
+ "gpt_max_text_tokens": 402,
108
+ "gpt_max_prompt_tokens": 70,
109
+ "gpt_layers": 30,
110
+ "gpt_n_model_channels": 1024,
111
+ "gpt_n_heads": 16,
112
+ "gpt_number_text_tokens": 6153,
113
+ "gpt_start_text_token": null,
114
+ "gpt_stop_text_token": null,
115
+ "gpt_num_audio_tokens": 1026,
116
+ "gpt_start_audio_token": 1024,
117
+ "gpt_stop_audio_token": 1025,
118
+ "gpt_code_stride_len": 1024,
119
+ "gpt_use_masking_gt_prompt_approach": true,
120
+ "gpt_use_perceiver_resampler": true,
121
+ "input_sample_rate": 22050,
122
+ "output_sample_rate": 24000,
123
+ "output_hop_length": 256,
124
+ "decoder_input_dim": 1024,
125
+ "d_vector_dim": 512,
126
+ "cond_d_vector_in_each_upsampling_layer": true,
127
+ "duration_const": 102400
128
+ },
129
+ "model_dir": null,
130
+ "languages": [
131
+ "en",
132
+ "es",
133
+ "fr",
134
+ "de",
135
+ "it",
136
+ "pt",
137
+ "pl",
138
+ "tr",
139
+ "ru",
140
+ "nl",
141
+ "cs",
142
+ "ar",
143
+ "zh-cn",
144
+ "hu",
145
+ "ko",
146
+ "ja"
147
+ ],
148
+ "temperature": 0.75,
149
+ "length_penalty": 1.0,
150
+ "repetition_penalty": 10.0,
151
+ "top_k": 50,
152
+ "top_p": 0.85,
153
+ "num_gpt_outputs": 1,
154
+ "gpt_cond_len": 30,
155
+ "gpt_cond_chunk_len": 4,
156
+ "max_ref_len": 30,
157
+ "sound_norm_refs": false
158
+ }
XTTS-v2_models/XTTS-v2_PeterJarvis/fromtts.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f523fe36e634b1f373da63346fe3fec4eb2ffe93091d9495ca199471ff649997
3
+ size 2027600
XTTS-v2_models/XTTS-v2_PeterJarvis/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6684f668f24cc92f702c5633b732169efa13004070a6293f916aac6844d6141
3
+ size 1863948438
XTTS-v2_models/XTTS-v2_PeterJarvis/peterdrury.jpg ADDED
XTTS-v2_models/XTTS-v2_PeterJarvis/reference copy.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a30e42fe11fbb9647cc70156c2d606c63601df13fdcb8792c78581d4d79e3e
3
+ size 1670584
XTTS-v2_models/XTTS-v2_PeterJarvis/reference.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a30e42fe11fbb9647cc70156c2d606c63601df13fdcb8792c78581d4d79e3e
3
+ size 1670584
XTTS-v2_models/XTTS-v2_PeterJarvis/speakers_xtts.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
3
+ size 7754818
XTTS-v2_models/XTTS-v2_PeterJarvis/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
XTTS-v2_models/XTTS-v2_S_Dogg/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
XTTS-v2_models/XTTS-v2_S_Dogg/README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: coqui-license-1.0.0
4
+ license_link: https://coqui.ai/cpml
5
+ ---
XTTS-v2_models/XTTS-v2_S_Dogg/config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_path": "output",
3
+ "logger_uri": null,
4
+ "run_name": "run",
5
+ "project_name": null,
6
+ "run_description": "\ud83d\udc38Coqui trainer run.",
7
+ "print_step": 25,
8
+ "plot_step": 100,
9
+ "model_param_stats": false,
10
+ "wandb_entity": null,
11
+ "dashboard_logger": "tensorboard",
12
+ "save_on_interrupt": true,
13
+ "log_model_step": null,
14
+ "save_step": 10000,
15
+ "save_n_checkpoints": 5,
16
+ "save_checkpoints": true,
17
+ "save_all_best": false,
18
+ "save_best_after": 10000,
19
+ "target_loss": null,
20
+ "print_eval": false,
21
+ "test_delay_epochs": 0,
22
+ "run_eval": true,
23
+ "run_eval_steps": null,
24
+ "distributed_backend": "nccl",
25
+ "distributed_url": "tcp://localhost:54321",
26
+ "mixed_precision": false,
27
+ "precision": "fp16",
28
+ "epochs": 1000,
29
+ "batch_size": 32,
30
+ "eval_batch_size": 16,
31
+ "grad_clip": 0.0,
32
+ "scheduler_after_epoch": true,
33
+ "lr": 0.001,
34
+ "optimizer": "radam",
35
+ "optimizer_params": null,
36
+ "lr_scheduler": null,
37
+ "lr_scheduler_params": {},
38
+ "use_grad_scaler": false,
39
+ "allow_tf32": false,
40
+ "cudnn_enable": true,
41
+ "cudnn_deterministic": false,
42
+ "cudnn_benchmark": false,
43
+ "training_seed": 54321,
44
+ "model": "xtts",
45
+ "num_loader_workers": 0,
46
+ "num_eval_loader_workers": 0,
47
+ "use_noise_augment": false,
48
+ "audio": {
49
+ "sample_rate": 22050,
50
+ "output_sample_rate": 24000
51
+ },
52
+ "use_phonemes": false,
53
+ "phonemizer": null,
54
+ "phoneme_language": null,
55
+ "compute_input_seq_cache": false,
56
+ "text_cleaner": null,
57
+ "enable_eos_bos_chars": false,
58
+ "test_sentences_file": "",
59
+ "phoneme_cache_path": null,
60
+ "characters": null,
61
+ "add_blank": false,
62
+ "batch_group_size": 0,
63
+ "loss_masking": null,
64
+ "min_audio_len": 1,
65
+ "max_audio_len": Infinity,
66
+ "min_text_len": 1,
67
+ "max_text_len": Infinity,
68
+ "compute_f0": false,
69
+ "compute_energy": false,
70
+ "compute_linear_spec": false,
71
+ "precompute_num_workers": 0,
72
+ "start_by_longest": false,
73
+ "shuffle": false,
74
+ "drop_last": false,
75
+ "datasets": [
76
+ {
77
+ "formatter": "",
78
+ "dataset_name": "",
79
+ "path": "",
80
+ "meta_file_train": "",
81
+ "ignored_speakers": null,
82
+ "language": "",
83
+ "phonemizer": "",
84
+ "meta_file_val": "",
85
+ "meta_file_attn_mask": ""
86
+ }
87
+ ],
88
+ "test_sentences": [],
89
+ "eval_split_max_size": null,
90
+ "eval_split_size": 0.01,
91
+ "use_speaker_weighted_sampler": false,
92
+ "speaker_weighted_sampler_alpha": 1.0,
93
+ "use_language_weighted_sampler": false,
94
+ "language_weighted_sampler_alpha": 1.0,
95
+ "use_length_weighted_sampler": false,
96
+ "length_weighted_sampler_alpha": 1.0,
97
+ "model_args": {
98
+ "gpt_batch_size": 1,
99
+ "enable_redaction": false,
100
+ "kv_cache": true,
101
+ "gpt_checkpoint": null,
102
+ "clvp_checkpoint": null,
103
+ "decoder_checkpoint": null,
104
+ "num_chars": 255,
105
+ "tokenizer_file": "",
106
+ "gpt_max_audio_tokens": 605,
107
+ "gpt_max_text_tokens": 402,
108
+ "gpt_max_prompt_tokens": 70,
109
+ "gpt_layers": 30,
110
+ "gpt_n_model_channels": 1024,
111
+ "gpt_n_heads": 16,
112
+ "gpt_number_text_tokens": 6153,
113
+ "gpt_start_text_token": null,
114
+ "gpt_stop_text_token": null,
115
+ "gpt_num_audio_tokens": 1026,
116
+ "gpt_start_audio_token": 1024,
117
+ "gpt_stop_audio_token": 1025,
118
+ "gpt_code_stride_len": 1024,
119
+ "gpt_use_masking_gt_prompt_approach": true,
120
+ "gpt_use_perceiver_resampler": true,
121
+ "input_sample_rate": 22050,
122
+ "output_sample_rate": 24000,
123
+ "output_hop_length": 256,
124
+ "decoder_input_dim": 1024,
125
+ "d_vector_dim": 512,
126
+ "cond_d_vector_in_each_upsampling_layer": true,
127
+ "duration_const": 102400
128
+ },
129
+ "model_dir": null,
130
+ "languages": [
131
+ "en",
132
+ "es",
133
+ "fr",
134
+ "de",
135
+ "it",
136
+ "pt",
137
+ "pl",
138
+ "tr",
139
+ "ru",
140
+ "nl",
141
+ "cs",
142
+ "ar",
143
+ "zh-cn",
144
+ "hu",
145
+ "ko",
146
+ "ja"
147
+ ],
148
+ "temperature": 0.75,
149
+ "length_penalty": 1.0,
150
+ "repetition_penalty": 10.0,
151
+ "top_k": 50,
152
+ "top_p": 0.85,
153
+ "num_gpt_outputs": 1,
154
+ "gpt_cond_len": 30,
155
+ "gpt_cond_chunk_len": 4,
156
+ "max_ref_len": 30,
157
+ "sound_norm_refs": false
158
+ }
XTTS-v2_models/XTTS-v2_S_Dogg/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc95f7b164b6791f86e5342c2db27dd4c82cadcc8390cf65f4340df464277515
3
+ size 1863948438
XTTS-v2_models/XTTS-v2_S_Dogg/reference.wav ADDED
Binary file (228 kB). View file
 
XTTS-v2_models/XTTS-v2_S_Dogg/speakers_xtts.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
3
+ size 7754818
XTTS-v2_models/XTTS-v2_S_Dogg/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
XTTS-v2_models/XTTS-v2_SamuelL/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ reference.wav filter=lfs diff=lfs merge=lfs -text
XTTS-v2_models/XTTS-v2_SamuelL/README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: coqui-license-1.0.0
4
+ license_link: https://coqui.ai/cpml
5
+ ---
XTTS-v2_models/XTTS-v2_SamuelL/config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_path": "output",
3
+ "logger_uri": null,
4
+ "run_name": "run",
5
+ "project_name": null,
6
+ "run_description": "\ud83d\udc38Coqui trainer run.",
7
+ "print_step": 25,
8
+ "plot_step": 100,
9
+ "model_param_stats": false,
10
+ "wandb_entity": null,
11
+ "dashboard_logger": "tensorboard",
12
+ "save_on_interrupt": true,
13
+ "log_model_step": null,
14
+ "save_step": 10000,
15
+ "save_n_checkpoints": 5,
16
+ "save_checkpoints": true,
17
+ "save_all_best": false,
18
+ "save_best_after": 10000,
19
+ "target_loss": null,
20
+ "print_eval": false,
21
+ "test_delay_epochs": 0,
22
+ "run_eval": true,
23
+ "run_eval_steps": null,
24
+ "distributed_backend": "nccl",
25
+ "distributed_url": "tcp://localhost:54321",
26
+ "mixed_precision": false,
27
+ "precision": "fp16",
28
+ "epochs": 1000,
29
+ "batch_size": 32,
30
+ "eval_batch_size": 16,
31
+ "grad_clip": 0.0,
32
+ "scheduler_after_epoch": true,
33
+ "lr": 0.001,
34
+ "optimizer": "radam",
35
+ "optimizer_params": null,
36
+ "lr_scheduler": null,
37
+ "lr_scheduler_params": {},
38
+ "use_grad_scaler": false,
39
+ "allow_tf32": false,
40
+ "cudnn_enable": true,
41
+ "cudnn_deterministic": false,
42
+ "cudnn_benchmark": false,
43
+ "training_seed": 54321,
44
+ "model": "xtts",
45
+ "num_loader_workers": 0,
46
+ "num_eval_loader_workers": 0,
47
+ "use_noise_augment": false,
48
+ "audio": {
49
+ "sample_rate": 22050,
50
+ "output_sample_rate": 24000
51
+ },
52
+ "use_phonemes": false,
53
+ "phonemizer": null,
54
+ "phoneme_language": null,
55
+ "compute_input_seq_cache": false,
56
+ "text_cleaner": null,
57
+ "enable_eos_bos_chars": false,
58
+ "test_sentences_file": "",
59
+ "phoneme_cache_path": null,
60
+ "characters": null,
61
+ "add_blank": false,
62
+ "batch_group_size": 0,
63
+ "loss_masking": null,
64
+ "min_audio_len": 1,
65
+ "max_audio_len": Infinity,
66
+ "min_text_len": 1,
67
+ "max_text_len": Infinity,
68
+ "compute_f0": false,
69
+ "compute_energy": false,
70
+ "compute_linear_spec": false,
71
+ "precompute_num_workers": 0,
72
+ "start_by_longest": false,
73
+ "shuffle": false,
74
+ "drop_last": false,
75
+ "datasets": [
76
+ {
77
+ "formatter": "",
78
+ "dataset_name": "",
79
+ "path": "",
80
+ "meta_file_train": "",
81
+ "ignored_speakers": null,
82
+ "language": "",
83
+ "phonemizer": "",
84
+ "meta_file_val": "",
85
+ "meta_file_attn_mask": ""
86
+ }
87
+ ],
88
+ "test_sentences": [],
89
+ "eval_split_max_size": null,
90
+ "eval_split_size": 0.01,
91
+ "use_speaker_weighted_sampler": false,
92
+ "speaker_weighted_sampler_alpha": 1.0,
93
+ "use_language_weighted_sampler": false,
94
+ "language_weighted_sampler_alpha": 1.0,
95
+ "use_length_weighted_sampler": false,
96
+ "length_weighted_sampler_alpha": 1.0,
97
+ "model_args": {
98
+ "gpt_batch_size": 1,
99
+ "enable_redaction": false,
100
+ "kv_cache": true,
101
+ "gpt_checkpoint": null,
102
+ "clvp_checkpoint": null,
103
+ "decoder_checkpoint": null,
104
+ "num_chars": 255,
105
+ "tokenizer_file": "",
106
+ "gpt_max_audio_tokens": 605,
107
+ "gpt_max_text_tokens": 402,
108
+ "gpt_max_prompt_tokens": 70,
109
+ "gpt_layers": 30,
110
+ "gpt_n_model_channels": 1024,
111
+ "gpt_n_heads": 16,
112
+ "gpt_number_text_tokens": 6153,
113
+ "gpt_start_text_token": null,
114
+ "gpt_stop_text_token": null,
115
+ "gpt_num_audio_tokens": 1026,
116
+ "gpt_start_audio_token": 1024,
117
+ "gpt_stop_audio_token": 1025,
118
+ "gpt_code_stride_len": 1024,
119
+ "gpt_use_masking_gt_prompt_approach": true,
120
+ "gpt_use_perceiver_resampler": true,
121
+ "input_sample_rate": 22050,
122
+ "output_sample_rate": 24000,
123
+ "output_hop_length": 256,
124
+ "decoder_input_dim": 1024,
125
+ "d_vector_dim": 512,
126
+ "cond_d_vector_in_each_upsampling_layer": true,
127
+ "duration_const": 102400
128
+ },
129
+ "model_dir": null,
130
+ "languages": [
131
+ "en",
132
+ "es",
133
+ "fr",
134
+ "de",
135
+ "it",
136
+ "pt",
137
+ "pl",
138
+ "tr",
139
+ "ru",
140
+ "nl",
141
+ "cs",
142
+ "ar",
143
+ "zh-cn",
144
+ "hu",
145
+ "ko",
146
+ "ja"
147
+ ],
148
+ "temperature": 0.75,
149
+ "length_penalty": 1.0,
150
+ "repetition_penalty": 10.0,
151
+ "top_k": 50,
152
+ "top_p": 0.85,
153
+ "num_gpt_outputs": 1,
154
+ "gpt_cond_len": 30,
155
+ "gpt_cond_chunk_len": 4,
156
+ "max_ref_len": 30,
157
+ "sound_norm_refs": false
158
+ }
XTTS-v2_models/XTTS-v2_SamuelL/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6369dc3bd2d4247c4ca3fcab9e0f4457414e7926545602305c69ca5685f6d60
3
+ size 1863948438
XTTS-v2_models/XTTS-v2_SamuelL/speakers_xtts.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
3
+ size 7754818
XTTS-v2_models/XTTS-v2_SamuelL/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
XTTS-v2_models/XTTS-v2_Yuki-Chan/.gitattributes ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ reference.wav filter=lfs diff=lfs merge=lfs -text
37
+ reference2.wav filter=lfs diff=lfs merge=lfs -text
38
+ sample_carlig.wav filter=lfs diff=lfs merge=lfs -text
39
+ reference[[:space:]]_readme.wav filter=lfs diff=lfs merge=lfs -text
40
+ reference_readme.wav filter=lfs diff=lfs merge=lfs -text
XTTS-v2_models/XTTS-v2_Yuki-Chan/LICENSE ADDED
File without changes
XTTS-v2_models/XTTS-v2_Yuki-Chan/LICENSE.txt ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Coqui Public Model License 1.0.0
2
+ https://coqui.ai/cpml.txt
3
+
4
+
5
+ This license allows only non-commercial use of a machine learning model and its outputs.
6
+
7
+
8
+ ## Acceptance
9
+
10
+
11
+ In order to get any license under these terms, you must agree to them as both strict obligations and conditions to all your licenses.
12
+
13
+
14
+ ## Licenses
15
+
16
+
17
+ The licensor grants you a copyright license to do everything you might do with the model that would otherwise infringe the licensor's copyright in it, for any non-commercial purpose. The licensor grants you a patent license that covers patent claims the licensor can license, or becomes able to license, that you would infringe by using the model in the form provided by
18
+ the licensor, for any non-commercial purpose.
19
+
20
+
21
+ ## Non-commercial Purpose
22
+
23
+
24
+ Non-commercial purposes include any of the following uses of the model or its output, but only so far as you do not receive any direct or indirect payment arising from the use of the model or its output.
25
+
26
+
27
+ ### Personal use for research, experiment, and testing for the benefit of public knowledge, personal study, private entertainment, hobby projects, amateur pursuits, or religious
28
+ observance.
29
+
30
+
31
+ ### Use by commercial or for-profit entities for testing, evaluation, or non-commercial research and development. Use of the model to train other models for commercial use is not a non-commercial purpose.
32
+
33
+
34
+ ### Use by any charitable organization for charitable purposes, or for testing or evaluation. Use for revenue-generating activity, including projects directly funded by government grants, is not a non-commercial purpose.
35
+
36
+
37
+ ## Notices
38
+
39
+
40
+ You must ensure that anyone who gets a copy of any part of the model, or any modification of the model, or their output, from you also gets a copy of these terms or the URL for them above.
41
+
42
+
43
+ ## No Other Rights
44
+
45
+
46
+ These terms do not allow you to sublicense or transfer any of your licenses to anyone else, or prevent the licensor from granting licenses to anyone else. These terms do not imply
47
+ any other licenses.
48
+
49
+
50
+ ## Patent Defense
51
+
52
+
53
+ If you make any written claim that the model infringes or contributes to infringement of any patent, your licenses for the model granted under these terms ends immediately. If your company makes such a claim, your patent license ends immediately for work on behalf of your company.
54
+
55
+
56
+ ## Violations
57
+
58
+
59
+ The first time you are notified in writing that you have violated any of these terms, or done anything with the model or its output that is not covered by your licenses, your licenses can nonetheless continue if you come into full compliance with these terms, and take practical steps to correct past violations, within 30 days of receiving notice. Otherwise, all your licenses
60
+ end immediately.
61
+
62
+
63
+ ## No Liability
64
+
65
+
66
+ ***As far as the law allows, the model and its output come as is, without any warranty or condition, and the licensor will not be liable to you for any damages arising out of these terms or the use or nature of the model or its output, under any kind of legal claim. If this provision is not enforceable in your jurisdiction, your licenses are void.***
67
+
68
+
69
+ ## Definitions
70
+
71
+
72
+ The **licensor** is the individual or entity offering these terms, and the **model** is the model the licensor makes available under these terms, including any documentation or similar information about the model.
73
+
74
+
75
+ **You** refers to the individual or entity agreeing to these terms.
76
+
77
+
78
+ **Your company** is any legal entity, sole proprietorship, or other kind of organization that you work for, plus all organizations that have control over, are under the control of, or are under common control with that organization. **Control** means ownership of substantially all the assets of an entity, or the power to direct its management and policies by vote, contract, or otherwise. Control can be direct or indirect.
79
+
80
+
81
+ **Your licenses** are all the licenses granted to you under these terms.
82
+
83
+
84
+ **Use** means anything you do with the model or its output requiring one of your licenses.
XTTS-v2_models/XTTS-v2_Yuki-Chan/README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: coqui-public-model-license
4
+ license_link: https://coqui.ai/cpml
5
+ library_name: coqui
6
+ pipeline_tag: text-to-speech
7
+ widget:
8
+ - text: "Once when I was six years old I saw a magnificent picture"
9
+ ---
10
+
11
+ # ⓍTTS_v2 - CarliG Fine-Tuned Model
12
+
13
+ This repository hosts a fine-tuned version of the ⓍTTS model, utilizing 2 minutes of unique voice lines from AtheneLive's CarliG AI, the iconic GPT4 Chatbot who went viral after the release of gpt4 api. The voice lines were sourced from athenes live streams which can be found here:
14
+ [AtheneLive George Carlin & CarliG livestream](https://www.youtube.com/watch?v=UMkZEQftZWA&t=5719s)
15
+
16
+ ![CarliG](carli_avatar_head.png)
17
+
18
+ Listen to a sample of the ⓍTTS_v2 - CarliG Fine-Tuned Model:
19
+
20
+ <audio controls>
21
+ <source src="https://huggingface.co/Borcherding/XTTS-v2_CarliG/raw/main/sample_carlig_readme.wav" type="audio/wav">
22
+ Your browser does not support the audio element.
23
+ </audio>
24
+
25
+ Here's a CarliG mp3 voice line clip from the training data:
26
+
27
+ <audio controls>
28
+ <source src="https://huggingface.co/Borcherding/XTTS-v2_CarliG/raw/main/reference.mp3" type="audio/wav">
29
+ Your browser does not support the audio element.
30
+ </audio>
31
+
32
+ ## Features
33
+ - 🎙️ **Voice Cloning**: Realistic voice cloning with just a short audio clip.
34
+ - 🌍 **Multi-Lingual Support**: Generates speech in 17 different languages while maintaining CarliG's distinct voice.
35
+ - 😃 **Emotion & Style Transfer**: Captures the emotional tone and style of the original voice.
36
+ - 🔄 **Cross-Language Cloning**: Maintains the unique voice characteristics across different languages.
37
+ - 🎧 **High-Quality Audio**: Outputs at a 24kHz sampling rate for clear and high-fidelity audio.
38
+
39
+ ## Supported Languages
40
+ The model supports the following 17 languages: English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt), Polish (pl), Turkish (tr), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (ko), and Hindi (hi).
41
+
42
+ ## Usage in Roll Cage
43
+ 🤖💬 Boost your AI experience with this Ollama add-on! Enjoy real-time audio 🎙️ and text 🔍 chats, LaTeX rendering 📜, agent automations ⚙️, workflows 🔄, text-to-image 📝➡️🖼️, image-to-text 🖼️➡️🔤, image-to-video 🖼️➡️🎥 transformations. Fine-tune text 📝, voice 🗣️, and image 🖼️ gens. Includes Windows macro controls 🖥️ and DuckDuckGo search.
44
+
45
+ [ollama_agent_roll_cage (OARC)](https://github.com/Leoleojames1/ollama_agent_roll_cage) is a completely local Python & CMD toolset add-on for the Ollama command line interface. The OARC toolset automates the creation of agents, giving the user more control over the likely output. It provides SYSTEM prompt templates for each ./Modelfile, allowing users to design and deploy custom agents quickly. Users can select which local model file is used in agent construction with the desired system prompt.
46
+
47
+ ## Why This Model for Roll Cage?
48
+ The CarliG fine-tuned model was designed for the Roll Cage chatbot to enhance user interaction with a familiar and beloved voice. By incorporating CarliG's distinctive speech patterns and tone, Roll Cage becomes more engaging and entertaining. The addition of multi-lingual support and emotion transfer ensures that the chatbot can communicate effectively and expressively across different languages and contexts, providing a more immersive experience for users.
49
+
50
+ ## CoquiTTS and Resources
51
+ - 🐸💬 **CoquiTTS**: [Coqui TTS on GitHub](https://github.com/coqui-ai/TTS)
52
+ - 📚 **Documentation**: [ReadTheDocs](https://tts.readthedocs.io/en/latest/)
53
+ - 👩‍💻 **Questions**: [GitHub Discussions](https://github.com/coqui-ai/TTS/discussions)
54
+ - 🗯 **Community**: [Discord](https://discord.gg/5eXr5seRrv)
55
+
56
+ ## License
57
+ This model is licensed under the [Coqui Public Model License](https://coqui.ai/cpml). Read more about the origin story of CPML [here](https://coqui.ai/blog/tts/cpml).
58
+
59
+ ## Contact
60
+ Join our 🐸Community on [Discord](https://discord.gg/fBC58unbKE) and follow us on [Twitter](https://twitter.com/coqui_ai). For inquiries, email us at [email protected].
61
+
62
+ Using 🐸TTS API:
63
+
64
+ ```python
65
+ from TTS.api import TTS
66
+ tts = TTS(model_path="D:/CodingGit_StorageHDD/Ollama_Custom_Mods/ollama_agent_roll_cage/AgentFiles/Ignored_TTS/XTTS-v2_CarliG/",
67
+ config_path="D:/CodingGit_StorageHDD/Ollama_Custom_Mods/ollama_agent_roll_cage/AgentFiles/Ignored_TTS/XTTS-v2_CarliG/config.json", progress_bar=False, gpu=True).to(self.device)
68
+
69
+ # generate speech by cloning a voice using default settings
70
+ tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
71
+ file_path="output.wav",
72
+ speaker_wav="/path/to/target/speaker.wav",
73
+ language="en")
74
+
75
+ ```
76
+
77
+ Using 🐸TTS Command line:
78
+
79
+ ```console
80
+ tts --model_name tts_models/multilingual/multi-dataset/xtts_v2 \
81
+ --text "Bugün okula gitmek istemiyorum." \
82
+ --speaker_wav /path/to/target/speaker.wav \
83
+ --language_idx tr \
84
+ --use_cuda true
85
+ ```
86
+
87
+ Using the model directly:
88
+
89
+ ```python
90
+ from TTS.tts.configs.xtts_config import XttsConfig
91
+ from TTS.tts.models.xtts import Xtts
92
+
93
+ config = XttsConfig()
94
+ config.load_json("/path/to/xtts/config.json")
95
+ model = Xtts.init_from_config(config)
96
+ model.load_checkpoint(config, checkpoint_dir="/path/to/xtts/", eval=True)
97
+ model.cuda()
98
+
99
+ outputs = model.synthesize(
100
+ "It took me quite a long time to develop a voice and now that I have it I am not going to be silent.",
101
+ config,
102
+ speaker_wav="/data/TTS-public/_refclips/3.wav",
103
+ gpt_cond_len=3,
104
+ language="en",
105
+ )
106
+ ```
XTTS-v2_models/XTTS-v2_Yuki-Chan/carli_avatar_head.png ADDED
XTTS-v2_models/XTTS-v2_Yuki-Chan/config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_path": "output",
3
+ "logger_uri": null,
4
+ "run_name": "run",
5
+ "project_name": null,
6
+ "run_description": "\ud83d\udc38Coqui trainer run.",
7
+ "print_step": 25,
8
+ "plot_step": 100,
9
+ "model_param_stats": false,
10
+ "wandb_entity": null,
11
+ "dashboard_logger": "tensorboard",
12
+ "save_on_interrupt": true,
13
+ "log_model_step": null,
14
+ "save_step": 10000,
15
+ "save_n_checkpoints": 5,
16
+ "save_checkpoints": true,
17
+ "save_all_best": false,
18
+ "save_best_after": 10000,
19
+ "target_loss": null,
20
+ "print_eval": false,
21
+ "test_delay_epochs": 0,
22
+ "run_eval": true,
23
+ "run_eval_steps": null,
24
+ "distributed_backend": "nccl",
25
+ "distributed_url": "tcp://localhost:54321",
26
+ "mixed_precision": false,
27
+ "precision": "fp16",
28
+ "epochs": 1000,
29
+ "batch_size": 32,
30
+ "eval_batch_size": 16,
31
+ "grad_clip": 0.0,
32
+ "scheduler_after_epoch": true,
33
+ "lr": 0.001,
34
+ "optimizer": "radam",
35
+ "optimizer_params": null,
36
+ "lr_scheduler": null,
37
+ "lr_scheduler_params": {},
38
+ "use_grad_scaler": false,
39
+ "allow_tf32": false,
40
+ "cudnn_enable": true,
41
+ "cudnn_deterministic": false,
42
+ "cudnn_benchmark": false,
43
+ "training_seed": 54321,
44
+ "model": "xtts",
45
+ "num_loader_workers": 0,
46
+ "num_eval_loader_workers": 0,
47
+ "use_noise_augment": false,
48
+ "audio": {
49
+ "sample_rate": 22050,
50
+ "output_sample_rate": 24000
51
+ },
52
+ "use_phonemes": false,
53
+ "phonemizer": null,
54
+ "phoneme_language": null,
55
+ "compute_input_seq_cache": false,
56
+ "text_cleaner": null,
57
+ "enable_eos_bos_chars": false,
58
+ "test_sentences_file": "",
59
+ "phoneme_cache_path": null,
60
+ "characters": null,
61
+ "add_blank": false,
62
+ "batch_group_size": 0,
63
+ "loss_masking": null,
64
+ "min_audio_len": 1,
65
+ "max_audio_len": Infinity,
66
+ "min_text_len": 1,
67
+ "max_text_len": Infinity,
68
+ "compute_f0": false,
69
+ "compute_energy": false,
70
+ "compute_linear_spec": false,
71
+ "precompute_num_workers": 0,
72
+ "start_by_longest": false,
73
+ "shuffle": false,
74
+ "drop_last": false,
75
+ "datasets": [
76
+ {
77
+ "formatter": "",
78
+ "dataset_name": "",
79
+ "path": "",
80
+ "meta_file_train": "",
81
+ "ignored_speakers": null,
82
+ "language": "",
83
+ "phonemizer": "",
84
+ "meta_file_val": "",
85
+ "meta_file_attn_mask": ""
86
+ }
87
+ ],
88
+ "test_sentences": [],
89
+ "eval_split_max_size": null,
90
+ "eval_split_size": 0.01,
91
+ "use_speaker_weighted_sampler": false,
92
+ "speaker_weighted_sampler_alpha": 1.0,
93
+ "use_language_weighted_sampler": false,
94
+ "language_weighted_sampler_alpha": 1.0,
95
+ "use_length_weighted_sampler": false,
96
+ "length_weighted_sampler_alpha": 1.0,
97
+ "model_args": {
98
+ "gpt_batch_size": 1,
99
+ "enable_redaction": false,
100
+ "kv_cache": true,
101
+ "gpt_checkpoint": null,
102
+ "clvp_checkpoint": null,
103
+ "decoder_checkpoint": null,
104
+ "num_chars": 255,
105
+ "tokenizer_file": "",
106
+ "gpt_max_audio_tokens": 605,
107
+ "gpt_max_text_tokens": 402,
108
+ "gpt_max_prompt_tokens": 70,
109
+ "gpt_layers": 30,
110
+ "gpt_n_model_channels": 1024,
111
+ "gpt_n_heads": 16,
112
+ "gpt_number_text_tokens": 6153,
113
+ "gpt_start_text_token": null,
114
+ "gpt_stop_text_token": null,
115
+ "gpt_num_audio_tokens": 1026,
116
+ "gpt_start_audio_token": 1024,
117
+ "gpt_stop_audio_token": 1025,
118
+ "gpt_code_stride_len": 1024,
119
+ "gpt_use_masking_gt_prompt_approach": true,
120
+ "gpt_use_perceiver_resampler": true,
121
+ "input_sample_rate": 22050,
122
+ "output_sample_rate": 24000,
123
+ "output_hop_length": 256,
124
+ "decoder_input_dim": 1024,
125
+ "d_vector_dim": 512,
126
+ "cond_d_vector_in_each_upsampling_layer": true,
127
+ "duration_const": 102400
128
+ },
129
+ "model_dir": null,
130
+ "languages": [
131
+ "en",
132
+ "es",
133
+ "fr",
134
+ "de",
135
+ "it",
136
+ "pt",
137
+ "pl",
138
+ "tr",
139
+ "ru",
140
+ "nl",
141
+ "cs",
142
+ "ar",
143
+ "zh-cn",
144
+ "hu",
145
+ "ko",
146
+ "ja"
147
+ ],
148
+ "temperature": 0.75,
149
+ "length_penalty": 1.0,
150
+ "repetition_penalty": 10.0,
151
+ "top_k": 50,
152
+ "top_p": 0.85,
153
+ "num_gpt_outputs": 1,
154
+ "gpt_cond_len": 30,
155
+ "gpt_cond_chunk_len": 4,
156
+ "max_ref_len": 30,
157
+ "sound_norm_refs": false
158
+ }
XTTS-v2_models/XTTS-v2_Yuki-Chan/dvae.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29bc227d410d4991e0a8c09b858f77415013eeb9fba9650258e96095557d97a
3
+ size 210514388
XTTS-v2_models/XTTS-v2_Yuki-Chan/hash.md5 ADDED
@@ -0,0 +1 @@
 
 
1
+ 10f92b55c512af7a8d39d650547a15a7
XTTS-v2_models/XTTS-v2_Yuki-Chan/mel_stats.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f69422a8a8f344c4fca2f0c6b8d41d2151d6615b7321e48e6bb15ae949b119c
3
+ size 1067
XTTS-v2_models/XTTS-v2_Yuki-Chan/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ccf4b4e5c3c7436e3da10f64d66b7ab6c9750b6b49f5403dbe5c49685520ae8
3
+ size 1863948502