Hugging Face's logo

TopSlayer
/
model

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
TopSlayer commited on
Commit
7f84218
·
verified ·
1 Parent(s): 4b127a1

End of training

Browse files
Files changed (6) hide show
  1. README.md +8 -7
  2. model.safetensors +1 -1
  3. runs/Jul21_11-36-58_cs-01k0p4mp7ex7fxc1hfkvvfygh8/events.out.tfevents.1753098100.cs-01k0p4mp7ex7fxc1hfkvvfygh8.52271.0 +3 -0
  4. runs/Jul21_11-58-17_cs-01k0p4mp7ex7fxc1hfkvvfygh8/events.out.tfevents.1753099400.cs-01k0p4mp7ex7fxc1hfkvvfygh8.55947.0 +3 -0
  5. runs/Jul21_12-09-24_cs-01k0p4mp7ex7fxc1hfkvvfygh8/events.out.tfevents.1753099999.cs-01k0p4mp7ex7fxc1hfkvvfygh8.60670.0 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 3.6245
22
  - Wer: 1.0
23
  - Cer: 1.0
24
 
@@ -39,7 +39,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 3e-05
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
@@ -47,7 +47,8 @@ The following hyperparameters were used during training:
47
  - total_train_batch_size: 32
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
  - lr_scheduler_type: linear
50
- - lr_scheduler_warmup_steps: 500
 
51
  - num_epochs: 30
52
  - mixed_precision_training: Native AMP
53
 
@@ -55,10 +56,10 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
  |:-------------:|:------:|:----:|:---------------:|:---:|:---:|
58
- | 5.867 | 1.9963 | 400 | 4.7211 | 1.0 | 1.0 |
59
- | 3.9734 | 3.9963 | 800 | 3.8661 | 1.0 | 1.0 |
60
- | 3.8277 | 5.9963 | 1200 | 3.8014 | 1.0 | 1.0 |
61
- | 3.7313 | 7.9963 | 1600 | 3.6245 | 1.0 | 1.0 |
62
 
63
 
64
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.9186
22
  - Wer: 1.0
23
  - Cer: 1.0
24
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
 
47
  - total_train_batch_size: 32
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
  - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - lr_scheduler_warmup_steps: 1000
52
  - num_epochs: 30
53
  - mixed_precision_training: Native AMP
54
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
58
  |:-------------:|:------:|:----:|:---------------:|:---:|:---:|
59
+ | 19.5696 | 0.9963 | 200 | 14.6766 | 1.0 | 1.0 |
60
+ | 5.7001 | 1.9963 | 400 | 4.9265 | 1.0 | 1.0 |
61
+ | 4.1247 | 2.9963 | 600 | 4.0528 | 1.0 | 1.0 |
62
+ | 3.9875 | 3.9963 | 800 | 3.9186 | 1.0 | 1.0 |
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a938469e1f7258ad0dd72fe0579c2e5a9b70551d3ec6bb4768e50d12d1d38538
3
  size 1262205180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454f53ff39ec0ea0c089f485bb2606caa3dfed465da8c03bed9e4f48a6a78c87
3
  size 1262205180
runs/Jul21_11-36-58_cs-01k0p4mp7ex7fxc1hfkvvfygh8/events.out.tfevents.1753098100.cs-01k0p4mp7ex7fxc1hfkvvfygh8.52271.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09f4988adcdaeaead0b8375393766129420154c10f4da7a98175777c89e7b7db
3
+ size 6565
runs/Jul21_11-58-17_cs-01k0p4mp7ex7fxc1hfkvvfygh8/events.out.tfevents.1753099400.cs-01k0p4mp7ex7fxc1hfkvvfygh8.55947.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf575642774f214912c9f8c0d10a11d973532b1f7f221abe59320f2201c5b8a
3
+ size 6772
runs/Jul21_12-09-24_cs-01k0p4mp7ex7fxc1hfkvvfygh8/events.out.tfevents.1753099999.cs-01k0p4mp7ex7fxc1hfkvvfygh8.60670.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7120188ec8655d7c4a701dd9eabdb780255c497ec554501e74f7c568ed50d86a
3
+ size 11747
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc78a7f8f8c20f650c4a14201b815bf3dbe9933f7d5a1fe9a9547121e8578283
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df6e8c340ccaa8fd58802b86ac773f534fcf05055a9146dc246abe8b9a632032
3
  size 5304