Hugging Face's logo

rse-mfm
/
whisper-large-v3-mfm

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
French
whisper
Generated from Trainer
Eval Results
Model card Files Metrics Community
rse-mfm commited on
Commit
0f2795d
·
verified ·
1 Parent(s): 46797cd

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Wer
25
  type: wer
26
- value: 8.54934793109
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the PX Corpus dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.3325
37
- - Wer: 8.5493
38
 
39
  ## Model description
40
 
@@ -65,12 +65,12 @@ The following hyperparameters were used during training:
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Wer |
69
- |:-------------:|:-------:|:----:|:---------------:|:------:|
70
- | 0.0024 | 14.0845 | 1000 | 0.2675 | 8.7265 |
71
- | 0.0 | 28.1690 | 2000 | 0.3135 | 8.5654 |
72
- | 0.0001 | 42.2535 | 3000 | 0.3283 | 8.5493 |
73
- | 0.0 | 56.3380 | 4000 | 0.3325 | 8.5493 |
74
 
75
 
76
  ### Framework versions
 
23
  metrics:
24
  - name: Wer
25
  type: wer
26
+ value: 8.597649331830622
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the PX Corpus dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.3224
37
+ - Wer: 8.5976
38
 
39
  ## Model description
40
 
 
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|
70
+ | 0.0035 | 14.0845 | 1000 | 0.2718 | 11.4635 |
71
+ | 0.0001 | 28.1690 | 2000 | 0.2975 | 8.5010 |
72
+ | 0.0002 | 42.2535 | 3000 | 0.3095 | 8.6137 |
73
+ | 0.0 | 56.3380 | 4000 | 0.3224 | 8.5976 |
74
 
75
 
76
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1506ce6e7f88b1907340531c3c78f174820bbe0b93e9f81310d7b5f9b71e287
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbbfe354c5c7866a4485ec9d9e46632170bc6f39362908953efecbbbceb3c3e1
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5553d87931fc17970f4707d8cd7b97e761907d383cedf75828b6255b97e5d994
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea55d204e93ac8f2f5c5adbc2516c1fed34f1c31368083287d207e2bf498c7a9
3
  size 1180663192