Hugging Face's logo

xuliu15
/
FT-10m

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
xuliu15 commited on
Commit
c98f348
·
verified ·
1 Parent(s): 3ed5505

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. model.safetensors +1 -1
  3. runs/May24_22-55-37_a100gpu5/events.out.tfevents.1716584159.a100gpu5.3263133.0 +2 -2
README.md CHANGED
@@ -20,7 +20,7 @@ model-index:
20
  metrics:
21
  - name: Wer
22
  type: wer
23
- value: 72.75540681564648
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,8 +30,8 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 6.1 dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 1.6189
34
- - Wer: 72.7554
35
 
36
  ## Model description
37
 
@@ -64,16 +64,16 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Wer |
66
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
67
- | 2.2806 | 25.0 | 200 | 2.4315 | 86.9013 |
68
- | 0.5256 | 50.0 | 400 | 1.6206 | 77.5451 |
69
- | 0.0145 | 75.0 | 600 | 1.5883 | 73.7378 |
70
- | 0.0055 | 100.0 | 800 | 1.6120 | 72.8274 |
71
- | 0.0044 | 125.0 | 1000 | 1.6189 | 72.7554 |
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.40.1
77
- - Pytorch 2.2.2+cu121
78
  - Datasets 2.19.0
79
  - Tokenizers 0.19.1
 
20
  metrics:
21
  - name: Wer
22
  type: wer
23
+ value: 75.45431645615172
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 6.1 dataset.
32
  It achieves the following results on the evaluation set:
33
+ - Loss: 1.7704
34
+ - Wer: 75.4543
35
 
36
  ## Model description
37
 
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Wer |
66
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
67
+ | 0.0024 | 25.0 | 200 | 1.6444 | 72.9821 |
68
+ | 0.0008 | 50.0 | 400 | 1.6951 | 73.5507 |
69
+ | 0.0004 | 75.0 | 600 | 1.7404 | 73.4895 |
70
+ | 0.0003 | 100.0 | 800 | 1.7631 | 74.6374 |
71
+ | 0.0002 | 125.0 | 1000 | 1.7704 | 75.4543 |
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.40.1
77
+ - Pytorch 2.3.0+cu121
78
  - Datasets 2.19.0
79
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ca2517dcc85d49d6afa41e8d349bea64c8311ce601e5993214dfb8698bd01d6
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da7a021e1487055957660f9b455edf60abc26ffc38c227704b15810e735c1584
3
  size 966995080
runs/May24_22-55-37_a100gpu5/events.out.tfevents.1716584159.a100gpu5.3263133.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28756cc30a00f74717238a9366552f9a3e099388b4c4fca99184d9901a20f642
3
- size 14448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3ce47da27a1f0114ad8e70f367255b7b9488ba4b3214ea71263c2c9a2e37ae
3
+ size 16808