End of training
Browse files
README.md
CHANGED
@@ -1,19 +1,48 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: openai/whisper-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
-
- name:
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
-
#
|
15 |
|
16 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -42,6 +71,42 @@ The following hyperparameters were used during training:
|
|
42 |
- training_steps: 3000
|
43 |
- mixed_precision_training: Native AMP
|
44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
### Framework versions
|
46 |
|
47 |
- Transformers 4.41.2
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- ga
|
4 |
+
- en
|
5 |
license: apache-2.0
|
6 |
base_model: openai/whisper-small
|
7 |
tags:
|
8 |
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- ymoslem/IWSLT2023-GA-EN
|
11 |
+
- ymoslem/FLEURS-GA-EN
|
12 |
+
- ymoslem/BitesizeIrish-GA-EN
|
13 |
+
- ymoslem/SpokenWords-GA-EN-MTed
|
14 |
+
metrics:
|
15 |
+
- bleu
|
16 |
+
- wer
|
17 |
model-index:
|
18 |
+
- name: Whisper Small GA-EN Speech Translation + VAD + warmup_ratio=0.01
|
19 |
+
results:
|
20 |
+
- task:
|
21 |
+
name: Automatic Speech Recognition
|
22 |
+
type: automatic-speech-recognition
|
23 |
+
dataset:
|
24 |
+
name: IWSLT-2023, FLEURS, BiteSize, and SpokenWords
|
25 |
+
type: ymoslem/IWSLT2023-GA-EN
|
26 |
+
metrics:
|
27 |
+
- name: Bleu
|
28 |
+
type: bleu
|
29 |
+
value: 29.94
|
30 |
+
- name: Wer
|
31 |
+
type: wer
|
32 |
+
value: 64.34038721296713
|
33 |
---
|
34 |
|
35 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
36 |
should probably proofread and complete it, then remove this comment. -->
|
37 |
|
38 |
+
# Whisper Small GA-EN Speech Translation + VAD + warmup_ratio=0.01
|
39 |
|
40 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IWSLT-2023, FLEURS, BiteSize, and SpokenWords dataset.
|
41 |
+
It achieves the following results on the evaluation set:
|
42 |
+
- Loss: 1.7482
|
43 |
+
- Bleu: 29.94
|
44 |
+
- Chrf: 45.74
|
45 |
+
- Wer: 64.3404
|
46 |
|
47 |
## Model description
|
48 |
|
|
|
71 |
- training_steps: 3000
|
72 |
- mixed_precision_training: Native AMP
|
73 |
|
74 |
+
### Training results
|
75 |
+
|
76 |
+
| Training Loss | Epoch | Step | Bleu | Chrf | Validation Loss | Wer |
|
77 |
+
|:-------------:|:------:|:----:|:-----:|:-----:|:---------------:|:--------:|
|
78 |
+
| 2.0518 | 0.2188 | 100 | 8.56 | 25.29 | 1.8072 | 123.9982 |
|
79 |
+
| 1.5449 | 0.4376 | 200 | 18.41 | 34.82 | 1.5746 | 83.7461 |
|
80 |
+
| 1.2518 | 0.6565 | 300 | 21.1 | 36.24 | 1.5009 | 83.9712 |
|
81 |
+
| 1.0947 | 0.8753 | 400 | 21.5 | 41.43 | 1.4582 | 89.8694 |
|
82 |
+
| 0.4439 | 1.0941 | 500 | 25.21 | 41.77 | 1.4979 | 72.5799 |
|
83 |
+
| 0.4416 | 1.3129 | 600 | 22.2 | 40.47 | 1.5107 | 79.8739 |
|
84 |
+
| 0.4417 | 1.5317 | 700 | 20.2 | 40.75 | 1.5215 | 88.8789 |
|
85 |
+
| 0.4108 | 1.7505 | 800 | 25.73 | 41.28 | 1.5278 | 67.8073 |
|
86 |
+
| 0.355 | 1.9694 | 900 | 20.6 | 39.37 | 1.5436 | 87.3030 |
|
87 |
+
| 0.1303 | 2.1882 | 1000 | 28.79 | 42.68 | 1.5936 | 68.1675 |
|
88 |
+
| 0.1421 | 2.4070 | 1100 | 27.84 | 42.58 | 1.5745 | 67.5371 |
|
89 |
+
| 0.1341 | 2.6258 | 1200 | 30.52 | 45.15 | 1.5953 | 66.5916 |
|
90 |
+
| 0.1365 | 2.8446 | 1300 | 26.93 | 43.72 | 1.6046 | 74.2909 |
|
91 |
+
| 0.0528 | 3.0635 | 1400 | 29.03 | 44.12 | 1.6303 | 64.8807 |
|
92 |
+
| 0.0519 | 3.2823 | 1500 | 27.75 | 44.34 | 1.6774 | 68.6177 |
|
93 |
+
| 0.0554 | 3.5011 | 1600 | 27.64 | 45.15 | 1.6637 | 71.1842 |
|
94 |
+
| 0.0514 | 3.7199 | 1700 | 30.26 | 44.62 | 1.6497 | 65.4660 |
|
95 |
+
| 0.0503 | 3.9387 | 1800 | 26.88 | 43.0 | 1.6780 | 70.4187 |
|
96 |
+
| 0.0259 | 4.1575 | 1900 | 29.6 | 44.51 | 1.6915 | 64.9707 |
|
97 |
+
| 0.0263 | 4.3764 | 2000 | 25.33 | 42.51 | 1.7080 | 72.3998 |
|
98 |
+
| 0.0254 | 4.5952 | 2100 | 30.59 | 45.35 | 1.6884 | 64.2954 |
|
99 |
+
| 0.0211 | 4.8140 | 2200 | 31.09 | 46.56 | 1.6984 | 64.0252 |
|
100 |
+
| 0.0137 | 5.0328 | 2300 | 28.96 | 43.67 | 1.7253 | 66.3665 |
|
101 |
+
| 0.0075 | 5.2516 | 2400 | 29.77 | 44.63 | 1.7112 | 66.9968 |
|
102 |
+
| 0.0056 | 5.4705 | 2500 | 29.96 | 45.51 | 1.7197 | 64.5655 |
|
103 |
+
| 0.0067 | 5.6893 | 2600 | 29.86 | 45.25 | 1.7464 | 66.0964 |
|
104 |
+
| 0.0064 | 5.9081 | 2700 | 29.47 | 45.36 | 1.7440 | 65.2859 |
|
105 |
+
| 0.0023 | 6.1269 | 2800 | 30.03 | 46.49 | 1.7419 | 64.4755 |
|
106 |
+
| 0.0016 | 6.3457 | 2900 | 29.76 | 45.64 | 1.7474 | 65.0158 |
|
107 |
+
| 0.0019 | 6.5646 | 3000 | 1.7482| 29.94 | 45.74 | 64.3404 |
|
108 |
+
|
109 |
+
|
110 |
### Framework versions
|
111 |
|
112 |
- Transformers 4.41.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f56a9be4b1e8cc46c27abcd4e63af60eaa2fde66a65951d2d50df227b260e5c
|
3 |
size 966995080
|
runs/Jun03_02-03-40_217bdb97c60e/events.out.tfevents.1717380240.217bdb97c60e
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:642ff70adf94ef9202b7105753f15c5e7f790ab47610d3a4647a90d15528d8d7
|
3 |
+
size 7262
|