EzraWilliam commited on
Commit
8bf0e09
1 Parent(s): c06b616

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: EzraWilliam/wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
17
 
18
- This model is a fine-tuned version of [EzraWilliam/wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1](https://huggingface.co/EzraWilliam/wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.7244
21
- - Wer: 1.0085
22
 
23
  ## Model description
24
 
@@ -43,16 +43,15 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - lr_scheduler_warmup_steps: 10000
47
  - num_epochs: 30
48
- - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-----:|:----:|:---------------:|:------:|
54
- | 0.4266 | 11.9 | 500 | 1.5595 | 0.9622 |
55
- | 0.3395 | 23.81 | 1000 | 1.7244 | 1.0085 |
56
 
57
 
58
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
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: 2.8876
21
+ - Wer: 1.0
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 5000
47
  - num_epochs: 30
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
53
+ | 7.1276 | 11.9 | 500 | 2.9936 | 1.0 |
54
+ | 2.8738 | 23.81 | 1000 | 2.8876 | 1.0 |
55
 
56
 
57
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f8da84486747dedba53c6185e880a76dc2b97d310e983ef18f53206ddd7ce2
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7419a47a21dbbf01c070c2a1c467c27013255f7508fd8ce79b7e41f005cfa9dc
3
  size 377611120
runs/Jan22_10-36-59_d1f9cb36e808/events.out.tfevents.1705919830.d1f9cb36e808.302.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61dbb69f8cf2de3d366b9b2bec8ef4b80a3952303c1abab96b661fe8b8008148
3
- size 7164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbecdbea68d2f190bec66ed601e36047212cbf168f379f55f84671cda11a1e7
3
+ size 7518