Hugging Face's logo

ndeclarke
/
wav2vec2-mms-1b-CV17.0-training_set_variations

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ndeclarke commited on
Commit
27fcd84
•
1 Parent(s): 0003c58

End of training

Browse files
Files changed (3) hide show
  1. README.md +30 -28
  2. adapter.tam-8192.safetensors +3 -0
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,20 +1,20 @@
1
  ---
 
 
2
  base_model: facebook/mms-1b-all
 
 
3
  datasets:
4
  - common_voice_17_0
5
- library_name: transformers
6
- license: cc-by-nc-4.0
7
  metrics:
8
  - wer
9
  - bleu
10
- tags:
11
- - generated_from_trainer
12
  model-index:
13
  - name: wav2vec2-mms-1b-CV17.0-training_set_variations
14
  results:
15
  - task:
16
- type: automatic-speech-recognition
17
  name: Automatic Speech Recognition
 
18
  dataset:
19
  name: common_voice_17_0
20
  type: common_voice_17_0
@@ -22,12 +22,12 @@ model-index:
22
  split: validation
23
  args: ta
24
  metrics:
25
- - type: wer
26
- value: 0.3699525493114998
27
- name: Wer
28
- - type: bleu
29
- value: 0.4072321954028345
30
- name: Bleu
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -37,10 +37,10 @@ should probably proofread and complete it, then remove this comment. -->
37
 
38
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_17_0 dataset.
39
  It achieves the following results on the evaluation set:
40
- - Loss: 0.2281
41
- - Wer: 0.3700
42
- - Cer: 0.0598
43
- - Bleu: 0.4072
44
 
45
  ## Model description
46
 
@@ -73,19 +73,21 @@ The following hyperparameters were used during training:
73
 
74
  ### Training results
75
 
76
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bleu |
77
- |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|:------:|
78
- | 7.0089 | 1.5625 | 100 | 0.2991 | 0.4260 | 0.0693 | 0.3354 |
79
- | 0.2087 | 3.125 | 200 | 0.2305 | 0.3968 | 0.0634 | 0.3678 |
80
- | 0.1924 | 4.6875 | 300 | 0.2291 | 0.3879 | 0.0624 | 0.3799 |
81
- | 0.1799 | 6.25 | 400 | 0.2290 | 0.3859 | 0.0629 | 0.3830 |
82
- | 0.1698 | 7.8125 | 500 | 0.2224 | 0.3700 | 0.0600 | 0.4119 |
83
- | 0.1587 | 9.375 | 600 | 0.2246 | 0.3672 | 0.0601 | 0.4129 |
84
- | 0.1547 | 10.9375 | 700 | 0.2176 | 0.3855 | 0.0604 | 0.3820 |
85
- | 0.1446 | 12.5 | 800 | 0.2273 | 0.3907 | 0.0619 | 0.3755 |
86
- | 0.1404 | 14.0625 | 900 | 0.2239 | 0.3713 | 0.0605 | 0.4035 |
87
- | 0.1333 | 15.625 | 1000 | 0.2261 | 0.3699 | 0.0602 | 0.4123 |
88
- | 0.1251 | 17.1875 | 1100 | 0.2281 | 0.3700 | 0.0598 | 0.4072 |
 
 
89
 
90
 
91
  ### Framework versions
 
1
  ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
  base_model: facebook/mms-1b-all
5
+ tags:
6
+ - generated_from_trainer
7
  datasets:
8
  - common_voice_17_0
 
 
9
  metrics:
10
  - wer
11
  - bleu
 
 
12
  model-index:
13
  - name: wav2vec2-mms-1b-CV17.0-training_set_variations
14
  results:
15
  - task:
 
16
  name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
  dataset:
19
  name: common_voice_17_0
20
  type: common_voice_17_0
 
22
  split: validation
23
  args: ta
24
  metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 0.3597180870859695
28
+ - name: Bleu
29
+ type: bleu
30
+ value: 0.4226157099926465
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
37
 
38
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_17_0 dataset.
39
  It achieves the following results on the evaluation set:
40
+ - Loss: 0.2047
41
+ - Wer: 0.3597
42
+ - Cer: 0.0579
43
+ - Bleu: 0.4226
44
 
45
  ## Model description
46
 
 
73
 
74
  ### Training results
75
 
76
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bleu |
77
+ |:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
78
+ | 6.3615 | 0.3906 | 100 | 0.2954 | 0.4162 | 0.0682 | 0.3508 |
79
+ | 0.2115 | 0.7812 | 200 | 0.2266 | 0.3822 | 0.0619 | 0.3888 |
80
+ | 0.1868 | 1.1719 | 300 | 0.2227 | 0.3755 | 0.0608 | 0.3981 |
81
+ | 0.1913 | 1.5625 | 400 | 0.2274 | 0.3912 | 0.0637 | 0.3779 |
82
+ | 0.1896 | 1.9531 | 500 | 0.2263 | 0.3858 | 0.0631 | 0.3867 |
83
+ | 0.1769 | 2.3438 | 600 | 0.2176 | 0.3785 | 0.0618 | 0.3942 |
84
+ | 0.1752 | 2.7344 | 700 | 0.2162 | 0.3816 | 0.0614 | 0.3887 |
85
+ | 0.1777 | 3.125 | 800 | 0.2098 | 0.3606 | 0.0582 | 0.4260 |
86
+ | 0.1747 | 3.5156 | 900 | 0.2078 | 0.3657 | 0.0585 | 0.4111 |
87
+ | 0.1672 | 3.9062 | 1000 | 0.2075 | 0.3770 | 0.0595 | 0.3920 |
88
+ | 0.1583 | 4.2969 | 1100 | 0.2060 | 0.3631 | 0.0580 | 0.4137 |
89
+ | 0.1713 | 4.6875 | 1200 | 0.2064 | 0.3664 | 0.0587 | 0.4118 |
90
+ | 0.1563 | 5.0781 | 1300 | 0.2047 | 0.3597 | 0.0579 | 0.4226 |
91
 
92
 
93
  ### Framework versions
adapter.tam-8192.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00aa05a41cf991401bb84e579ca0205e5775fd44310233e24e0a66ed99941e7
3
+ size 8926640
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd8c44d7ff01c71e2490ea1682c695d92032eb7c4ac1ca97bee5d1edc2a04525
3
  size 3859019024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9ea7bb8682d0d8606a8cf596da38e47f437e735e6fb238a31507bd076278cd
3
  size 3859019024