Model save

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model: openai/whisper-medium.en
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: whisper-medium.en-cit-do015-wd0-lr1e-06-1000
+ results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# whisper-medium.en-cit-do015-wd0-lr1e-06-1000
+
+This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6953
+- Wer Ortho: 26.2768
+- Wer: 14.7572
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- training_steps: 500
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
+| No log | 0.4444 | 25 | 1.5811 | 45.2632 | 31.9044 |
+| 1.7463 | 0.8889 | 50 | 1.3848 | 39.1033 | 27.0106 |
+| 1.7463 | 1.3333 | 75 | 1.2178 | 35.7505 | 23.0273 |
+| 1.3387 | 1.7778 | 100 | 1.0166 | 36.1014 | 23.4446 |
+| 1.3387 | 2.2222 | 125 | 0.8784 | 31.9298 | 19.1958 |
+| 0.988 | 2.6667 | 150 | 0.8340 | 30.8382 | 18.4750 |
+| 0.988 | 3.1111 | 175 | 0.8027 | 30.3314 | 17.7162 |
+| 0.8856 | 3.5556 | 200 | 0.7812 | 29.6686 | 17.4127 |
+| 0.8856 | 4.0 | 225 | 0.7651 | 30.1365 | 17.6783 |
+| 0.7927 | 4.4444 | 250 | 0.7515 | 29.2008 | 16.8816 |
+| 0.7927 | 4.8889 | 275 | 0.7402 | 28.2651 | 15.6677 |
+| 0.7482 | 5.3333 | 300 | 0.7300 | 27.9922 | 15.5159 |
+| 0.7482 | 5.7778 | 325 | 0.7217 | 27.8752 | 15.6677 |
+| 0.7275 | 6.2222 | 350 | 0.7153 | 27.4854 | 15.4021 |
+| 0.7275 | 6.6667 | 375 | 0.7085 | 27.3684 | 15.3642 |
+| 0.7003 | 7.1111 | 400 | 0.7041 | 26.6277 | 14.6813 |
+| 0.7003 | 7.5556 | 425 | 0.7002 | 26.3158 | 14.7572 |
+| 0.6763 | 8.0 | 450 | 0.6973 | 26.2378 | 14.6055 |
+| 0.6763 | 8.4444 | 475 | 0.6963 | 26.4327 | 14.7951 |
+| 0.6687 | 8.8889 | 500 | 0.6953 | 26.2768 | 14.7572 |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 1.13.1+cu117
+- Datasets 2.20.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,188 @@
+{
+ "alignment_heads": [
+ [
+ 11,
+ 4
+ ],
+ [
+ 14,
+ 1
+ ],
+ [
+ 14,
+ 12
+ ],
+ [
+ 14,
+ 14
+ ],
+ [
+ 15,
+ 4
+ ],
+ [
+ 16,
+ 0
+ ],
+ [
+ 16,
+ 4
+ ],
+ [
+ 16,
+ 9
+ ],
+ [
+ 17,
+ 12
+ ],
+ [
+ 17,
+ 14
+ ],
+ [
+ 18,
+ 7
+ ],
+ [
+ 18,
+ 10
+ ],
+ [
+ 18,
+ 15
+ ],
+ [
+ 20,
+ 0
+ ],
+ [
+ 20,
+ 3
+ ],
+ [
+ 20,
+ 9
+ ],
+ [
+ 20,
+ 14
+ ],
+ [
+ 21,
+ 12
+ ]
+ ],
+ "begin_suppress_tokens": [
+ 220,
+ 50256
+ ],
+ "bos_token_id": 50257,
+ "decoder_start_token_id": 50257,
+ "eos_token_id": 50256,
+ "is_multilingual": false,
+ "max_initial_timestamp_index": 50,
+ "max_length": 448,
+ "no_timestamps_token_id": 50362,
+ "pad_token_id": 50256,
+ "prev_sot_token_id": 50360,
+ "return_timestamps": false,
+ "suppress_tokens": [
+ 1,
+ 2,
+ 7,
+ 8,
+ 9,
+ 10,
+ 14,
+ 25,
+ 26,
+ 27,
+ 28,
+ 29,
+ 31,
+ 58,
+ 59,
+ 60,
+ 61,
+ 62,
+ 63,
+ 90,
+ 91,
+ 92,
+ 93,
+ 357,
+ 366,
+ 438,
+ 532,
+ 685,
+ 705,
+ 796,
+ 930,
+ 1058,
+ 1220,
+ 1267,
+ 1279,
+ 1303,
+ 1343,
+ 1377,
+ 1391,
+ 1635,
+ 1782,
+ 1875,
+ 2162,
+ 2361,
+ 2488,
+ 3467,
+ 4008,
+ 4211,
+ 4600,
+ 4808,
+ 5299,
+ 5855,
+ 6329,
+ 7203,
+ 9609,
+ 9959,
+ 10563,
+ 10786,
+ 11420,
+ 11709,
+ 11907,
+ 13163,
+ 13697,
+ 13700,
+ 14808,
+ 15306,
+ 16410,
+ 16791,
+ 17992,
+ 19203,
+ 19510,
+ 20724,
+ 22305,
+ 22935,
+ 27007,
+ 30109,
+ 30420,
+ 33409,
+ 34949,
+ 40283,
+ 40493,
+ 40549,
+ 47282,
+ 49146,
+ 50257,
+ 50357,
+ 50358,
+ 50359,
+ 50360,
+ 50361
+ ],
+ "task": "transcribe",
+ "task_to_id": {
+ "transcribe": 50359,
+ "translate": 50358
+ },
+ "transformers_version": "4.42.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2782a43fb7f18db93df1ddb9cb239ece45285f77b32824240527094609e67c2f
+oid sha256:b4ac9f52ebc724709d0eda485449a3f2b1303aa88ac63a5e1fafadaa6c9bc0b0
 size 1634043280

runs/Jul02_10-38-19_whisper-finetune2/events.out.tfevents.1719916708.whisper-finetune2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c78c2a8edb04b6f414b0ad2d308b83977e07aba0773d2c9569387270d4352943
-size 16136
+oid sha256:9e7d8efc14f8e226db226b8fd8b08b2eed992512d3f654fb6aeac87bd272ff37
+size 16490