Hugging Face's logo

Rziane
/
wav2vec2-large-mms-1b-tun_test

Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
Rziane commited on
Commit
df96cf8
·
verified ·
1 Parent(s): cbf3608

End of training

Browse files
Files changed (3) hide show
  1. README.md +17 -18
  2. adapter.aeb.safetensors +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
- base_model: facebook/mms-1b-all
3
  license: cc-by-nc-4.0
4
- metrics:
5
- - wer
6
  tags:
7
  - generated_from_trainer
 
 
8
  model-index:
9
  - name: wav2vec2-large-mms-1b-tun_test
10
  results: []
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: inf
21
- - Wer: 0.8515
22
 
23
  ## Model description
24
 
@@ -44,24 +44,23 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
- - num_epochs: 4
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:------:|:----:|:---------------:|:------:|
54
- | 5.6344 | 0.3413 | 100 | inf | 0.9989 |
55
- | 2.6597 | 0.6826 | 200 | inf | 0.9366 |
56
- | 2.4563 | 1.0239 | 300 | inf | 0.9217 |
57
- | 2.2889 | 1.3652 | 400 | inf | 0.8920 |
58
- | 2.3851 | 1.7065 | 500 | inf | 0.8801 |
59
- | 2.2111 | 2.0478 | 600 | inf | 0.8737 |
60
- | 2.3228 | 2.3891 | 700 | inf | 0.8682 |
61
- | 2.1423 | 2.7304 | 800 | inf | 0.8628 |
62
- | 2.1434 | 3.0717 | 900 | inf | 0.8600 |
63
- | 2.1972 | 3.4130 | 1000 | inf | 0.8538 |
64
- | 2.1034 | 3.7543 | 1100 | inf | 0.8515 |
65
 
66
 
67
  ### Framework versions
 
1
  ---
 
2
  license: cc-by-nc-4.0
3
+ base_model: facebook/mms-1b-all
 
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: wav2vec2-large-mms-1b-tun_test
10
  results: []
 
18
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: inf
21
+ - Wer: 0.8202
22
 
23
  ## Model description
24
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
+ - num_epochs: 10
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 2.7143 | 1.0 | 293 | inf | 0.9356 |
55
+ | 2.3549 | 2.0 | 586 | inf | 0.8881 |
56
+ | 2.2428 | 3.0 | 879 | inf | 0.8788 |
57
+ | 2.2523 | 4.0 | 1172 | inf | 0.8702 |
58
+ | 2.1636 | 5.0 | 1465 | inf | 0.8788 |
59
+ | 2.0924 | 6.0 | 1758 | inf | 0.8405 |
60
+ | 1.9987 | 7.0 | 2051 | inf | 0.8265 |
61
+ | 1.9648 | 8.0 | 2344 | inf | 0.8257 |
62
+ | 1.9403 | 9.0 | 2637 | inf | 0.8292 |
63
+ | 1.9393 | 10.0 | 2930 | inf | 0.8202 |
 
64
 
65
 
66
  ### Framework versions
adapter.aeb.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:470a2ffaf30aae7081aa9b2765633803174cdde381f5833fe46104788d70a31b
3
  size 8942020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7409dd0ea5bb5666409a7e6d05e49c421323efd670ddcd8a9209f7c9386b1db9
3
  size 8942020
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ada5778c3481341d909a85f6ab9f7e4e069557f4f20d8c23ad961d1bd9bbfebd
3
  size 3859034396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f061e0286b57466133b44dfd0914d0b6d08c942e3b95798146245a379c361b40
3
  size 3859034396