Hugging Face's logo

MathildeB3
/
52Hz-small-fr-v3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
French
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
1
MathildeB3 commited on
Commit
50b59f2
·
verified ·
1 Parent(s): 4c95ae4

Model save

Browse files
Files changed (3) hide show
  1. README.md +79 -0
  2. model.safetensors +1 -1
  3. runs/Feb15_19-42-59_sl-tp-br-517/events.out.tfevents.1771180981.sl-tp-br-517.1401463.0 +2 -2
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: openai/whisper-small
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: 52Hz-small-fr-v3
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # 52Hz-small-fr-v3
18
+
19
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4085
22
+ - Wer: 17.6471
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 4
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 16
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 15
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
+ | 1.461 | 1.0 | 22 | 0.8945 | 41.0131 |
58
+ | 0.6454 | 2.0 | 44 | 0.5209 | 25.4902 |
59
+ | 0.3068 | 3.0 | 66 | 0.4752 | 21.0784 |
60
+ | 0.2361 | 4.0 | 88 | 0.4253 | 19.9346 |
61
+ | 0.1448 | 5.0 | 110 | 0.4112 | 19.7712 |
62
+ | 0.1367 | 6.0 | 132 | 0.4118 | 17.9739 |
63
+ | 0.0945 | 7.0 | 154 | 0.4220 | 19.6078 |
64
+ | 0.0575 | 8.0 | 176 | 0.4065 | 16.9935 |
65
+ | 0.0421 | 9.0 | 198 | 0.4356 | 17.6471 |
66
+ | 0.0414 | 10.0 | 220 | 0.4186 | 17.8105 |
67
+ | 0.027 | 11.0 | 242 | 0.4105 | 17.3203 |
68
+ | 0.0249 | 12.0 | 264 | 0.4037 | 16.9935 |
69
+ | 0.0314 | 13.0 | 286 | 0.4077 | 17.3203 |
70
+ | 0.0214 | 14.0 | 308 | 0.4085 | 17.6471 |
71
+ | 0.0148 | 15.0 | 330 | 0.4085 | 17.6471 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.57.3
77
+ - Pytorch 2.9.1+cu130
78
+ - Datasets 4.4.2
79
+ - Tokenizers 0.22.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65a0d5881d44a739848c0164cb0216912f731f5b9acd47e88761d531b121be70
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20afb5f122b0182049d8446b95cd264a740ca69019782026334bf7bc10c688b8
3
  size 966995080
runs/Feb15_19-42-59_sl-tp-br-517/events.out.tfevents.1771180981.sl-tp-br-517.1401463.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b487aa5fb3deb96c5e4941d843f7570543358374966dd9bd2ddf698d65d03569
3
- size 25325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec920b61b41e460756afbfdf5ff3498835eab999480a5e77f79d2f9bb0ea2edb
3
+ size 25679