Hugging Face's logo

3funnn
/
wav2vec2-base-librispeech

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
3funnn commited on
Commit
58d0886
•
1 Parent(s): 409ebf1

3funnn/wav2vec2-base-librispeech

Browse files
Files changed (3) hide show
  1. README.md +11 -8
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.44274809160305345
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the librispeech_asr_dummy dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.8630
36
- - Wer: 0.4427
37
 
38
  ## Model description
39
 
@@ -59,15 +59,18 @@ The following hyperparameters were used during training:
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_steps: 1000
62
- - num_epochs: 60
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Wer |
68
- |:-------------:|:-----:|:----:|:---------------:|:------:|
69
- | 0.0416 | 29.41 | 500 | 0.8917 | 0.4275 |
70
- | 0.0419 | 58.82 | 1000 | 0.8630 | 0.4427 |
 
 
 
71
 
72
 
73
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.4069767441860465
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the librispeech_asr_dummy dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.9548
36
+ - Wer: 0.4070
37
 
38
  ## Model description
39
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_steps: 1000
62
+ - num_epochs: 150
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:------:|:----:|:---------------:|:------:|
69
+ | 4.4865 | 29.41 | 500 | 3.5010 | 1.0 |
70
+ | 1.112 | 58.82 | 1000 | 1.0382 | 0.4767 |
71
+ | 0.111 | 88.24 | 1500 | 0.9833 | 0.5116 |
72
+ | 0.0438 | 117.65 | 2000 | 0.9302 | 0.4302 |
73
+ | 0.0241 | 147.06 | 2500 | 0.9548 | 0.4070 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1847fb1e5d2d947d0513bbd7540941b05e1e5a1ffe4f2723843dabe99f44d15
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80aab74519da04c3e1b6456b4bd02234f14a33f09445bcf8d244a736d2af8818
3
  size 377611120
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c89b73041266f6648f183f495b20907220e61d520b22355abc359f3f64d2be0c
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5da6855d990d2d990e877d90e57036a3f8a2e81150b11889f65d81c776c8935
3
  size 4728