Hugging Face's logo

weewtr1121
/
outs

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
weewtr1121 commited on
Commit
54df004
•
1 Parent(s): cb155ad

./outs

Browse files
Files changed (6) hide show
  1. README.md +14 -2
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. preprocessor_config.json +1 -1
  5. runs/Oct08_13-50-17_bba3eca5875a/events.out.tfevents.1728395476.bba3eca5875a.858.0 +3 -0
  6. training_args.bin +2 -2
README.md CHANGED
@@ -15,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
  # outs
16
 
17
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
 
 
 
18
 
19
  ## Model description
20
 
@@ -42,9 +45,18 @@ The following hyperparameters were used during training:
42
  - num_epochs: 3.0
43
  - mixed_precision_training: Native AMP
44
 
 
 
 
 
 
 
 
 
 
45
  ### Framework versions
46
 
47
  - Transformers 4.44.2
48
- - Pytorch 2.4.0
49
- - Datasets 3.0.0
50
  - Tokenizers 0.19.1
 
15
  # outs
16
 
17
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6104
20
+ - Cer: 25.0366
21
 
22
  ## Model description
23
 
 
45
  - num_epochs: 3.0
46
  - mixed_precision_training: Native AMP
47
 
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
51
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
52
+ | 0.3211 | 1.0 | 1073 | 0.7999 | 39.8078 |
53
+ | 0.0795 | 2.0 | 2146 | 0.6431 | 23.1977 |
54
+ | 0.0101 | 3.0 | 3219 | 0.6104 | 25.0366 |
55
+
56
+
57
  ### Framework versions
58
 
59
  - Transformers 4.44.2
60
+ - Pytorch 2.4.1+cu121
61
+ - Datasets 3.0.1
62
  - Tokenizers 0.19.1
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08e0005225b3dbaf55dd13ac62926cc7e02c1025d66fa375e6fb305ff79cd4f9
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d1d40ae565f16909d102b1e1ac9a60b9fa0c201bc31142bb677696669ea76f
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:630ca774672856d2e0e39a702e590f635a1cfc5726a64b6578ab46dd367369a9
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae548e4cdab40fc2f435f71068d9b78ec784d44ff926bcffe6f71e09887603f
3
  size 1180663192
preprocessor_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "chunk_length": 30,
3
  "feature_extractor_type": "WhisperFeatureExtractor",
4
- "feature_size": 80,
5
  "hop_length": 160,
6
  "n_fft": 400,
7
  "n_samples": 480000,
 
1
  {
2
  "chunk_length": 30,
3
  "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
  "hop_length": 160,
6
  "n_fft": 400,
7
  "n_samples": 480000,
runs/Oct08_13-50-17_bba3eca5875a/events.out.tfevents.1728395476.bba3eca5875a.858.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2834a2bcdd2f9cc712b66679cd413a89a5f4996e71b7f43797ccca11c52a01
3
+ size 13699
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82b56e9ffce81276752ed6be8b21c4c87353081fda6f345ba9f6e7803ee9db2f
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06fad7890ce3cf6185ec9294223ebb0348aed4fde156a6b405a801d12bc04ca9
3
+ size 5304