Hugging Face's logo

Udap10
/
wav2vec2-large-mms-1b-dzo-colab-3

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
Udap10 commited on
Commit
08db0de
·
verified ·
1 Parent(s): 5abe25b

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -13
  2. adapter.dzo.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5800
22
- - Wer: 0.4672
23
 
24
  ## Model description
25
 
@@ -38,7 +38,7 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 0.005
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 8.473 | 1.0 | 20 | 6.5541 | 1.0505 |
56
- | 3.4553 | 2.0 | 40 | 3.1408 | 1.0 |
57
- | 2.6261 | 3.0 | 60 | 2.0645 | 0.9461 |
58
- | 1.1757 | 4.0 | 80 | 0.8704 | 0.6540 |
59
- | 0.8657 | 5.0 | 100 | 0.6830 | 0.5446 |
60
- | 0.7318 | 6.0 | 120 | 0.6215 | 0.5008 |
61
- | 0.6546 | 7.0 | 140 | 0.5725 | 0.4705 |
62
- | 0.5496 | 8.0 | 160 | 0.5756 | 0.4672 |
63
- | 0.5476 | 9.0 | 180 | 0.5708 | 0.4705 |
64
- | 0.5114 | 10.0 | 200 | 0.5800 | 0.4672 |
65
 
66
 
67
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5807
22
+ - Wer: 0.4336
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 0.004
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 8.6531 | 1.0 | 20 | 7.3871 | 1.0 |
56
+ | 3.365 | 2.0 | 40 | 3.0972 | 1.0 |
57
+ | 2.3227 | 3.0 | 60 | 1.8379 | 0.8684 |
58
+ | 1.1025 | 4.0 | 80 | 0.9537 | 0.6287 |
59
+ | 0.8483 | 5.0 | 100 | 0.7576 | 0.5405 |
60
+ | 0.7097 | 6.0 | 120 | 0.6485 | 0.5041 |
61
+ | 0.659 | 7.0 | 140 | 0.6432 | 0.4912 |
62
+ | 0.5759 | 8.0 | 160 | 0.6042 | 0.4853 |
63
+ | 0.5178 | 9.0 | 180 | 0.5881 | 0.4630 |
64
+ | 0.4767 | 10.0 | 200 | 0.5807 | 0.4336 |
65
 
66
 
67
  ### Framework versions
adapter.dzo.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3150a7dcd5b9c92f4d9992ddcde473b130ee6d1605c3bc25621ff819b7487df
3
  size 8952268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc66954039beca1bcafcb747bcc85ddf138a65307bd5d3204e285071711e156
3
  size 8952268