Hugging Face's logo

alslqk
/
wav2vec2-base-timit-demo-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
alslqk commited on
Commit
e9f480c
•
1 Parent(s): 28644d7

End of training

Browse files
Files changed (3) hide show
  1. README.md +12 -12
  2. model.safetensors +1 -1
  3. runs/Jul10_08-01-14_23aba7016ade/events.out.tfevents.1720598595.23aba7016ade.459.0 +2 -2
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
- base_model: facebook/wav2vec2-base
3
  license: apache-2.0
4
- metrics:
5
- - wer
6
  tags:
7
  - generated_from_trainer
 
 
8
  model-index:
9
  - name: wav2vec2-base-timit-demo-colab
10
  results: []
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4624
21
- - Wer: 0.3356
22
 
23
  ## Model description
24
 
@@ -51,13 +51,13 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
- | 3.2522 | 4.0 | 500 | 1.0927 | 0.8016 |
55
- | 0.5867 | 8.0 | 1000 | 0.4637 | 0.4332 |
56
- | 0.2368 | 12.0 | 1500 | 0.4241 | 0.3803 |
57
- | 0.1318 | 16.0 | 2000 | 0.3985 | 0.3639 |
58
- | 0.0896 | 20.0 | 2500 | 0.4723 | 0.3587 |
59
- | 0.0622 | 24.0 | 3000 | 0.4885 | 0.3422 |
60
- | 0.0458 | 28.0 | 3500 | 0.4624 | 0.3356 |
61
 
62
 
63
  ### Framework versions
 
1
  ---
 
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
 
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: wav2vec2-base-timit-demo-colab
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4374
21
+ - Wer: 0.3392
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 3.364 | 4.0 | 500 | 1.2339 | 0.9609 |
55
+ | 0.5751 | 8.0 | 1000 | 0.4374 | 0.4287 |
56
+ | 0.2175 | 12.0 | 1500 | 0.4184 | 0.3809 |
57
+ | 0.1281 | 16.0 | 2000 | 0.4357 | 0.3720 |
58
+ | 0.0889 | 20.0 | 2500 | 0.4152 | 0.3481 |
59
+ | 0.0604 | 24.0 | 3000 | 0.4518 | 0.3447 |
60
+ | 0.0471 | 28.0 | 3500 | 0.4374 | 0.3392 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9148bc128e64fdbf25d62407ab2eb7aec36ddf5aa4ce8581baa03e1af809c6ce
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de9bda711d385e2f1ace990f4db8b4bac9e7191cbb2d66150fd97f4d5e7bca03
3
  size 377611120
runs/Jul10_08-01-14_23aba7016ade/events.out.tfevents.1720598595.23aba7016ade.459.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec7319bd995261283b9d22d574085033e19a2ace4a4482bc87963cf95d4b0c10
3
- size 10256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512fa96b6e71704594efaa4d59f03c50e60d7afa4797e7d153147e31d01e2888
3
+ size 10610