Hugging Face's logo

EzraWilliam
/
wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod9

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
EzraWilliam commited on
Commit
1575c76
•
1 Parent(s): ddbd9c5

End of training

Browse files
Files changed (3) hide show
  1. README.md +61 -30
  2. model.safetensors +1 -1
  3. runs/Mar30_17-02-06_c69b10fbdf16/events.out.tfevents.1711818161.c69b10fbdf16.5538.0 +2 -2
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: facebook/wav2vec2-large-xlsr-53
6
  datasets:
7
  - xtreme_s
8
  metrics:
@@ -11,8 +11,8 @@ model-index:
11
  - name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod9
12
  results:
13
  - task:
14
- type: automatic-speech-recognition
15
  name: Automatic Speech Recognition
 
16
  dataset:
17
  name: xtreme_s
18
  type: xtreme_s
@@ -20,9 +20,9 @@ model-index:
20
  split: test
21
  args: fleurs.id_id
22
  metrics:
23
- - type: wer
24
- value: 0.9842089507558749
25
- name: Wer
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the xtreme_s dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.3012
36
- - Wer: 0.9842
37
 
38
  ## Model description
39
 
@@ -58,38 +58,69 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 20
 
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
- | No log | 1.0 | 39 | 2.8812 | 1.0 |
69
- | No log | 2.0 | 78 | 2.8688 | 1.0 |
70
- | No log | 3.0 | 117 | 2.8722 | 1.0 |
71
- | No log | 4.0 | 156 | 2.8640 | 1.0 |
72
- | No log | 5.0 | 195 | 2.8447 | 1.0 |
73
- | No log | 6.0 | 234 | 2.8468 | 1.0 |
74
- | No log | 7.0 | 273 | 2.8465 | 1.0 |
75
- | No log | 8.0 | 312 | 2.8488 | 1.0 |
76
- | No log | 9.0 | 351 | 2.8355 | 1.0 |
77
- | No log | 10.0 | 390 | 2.8167 | 1.0 |
78
- | No log | 11.0 | 429 | 2.8076 | 1.0 |
79
- | No log | 12.0 | 468 | 2.7065 | 1.0 |
80
- | 2.9881 | 13.0 | 507 | 2.5506 | 1.0 |
81
- | 2.9881 | 14.0 | 546 | 2.2657 | 1.0 |
82
- | 2.9881 | 15.0 | 585 | 1.9921 | 1.0 |
83
- | 2.9881 | 16.0 | 624 | 1.7390 | 1.0 |
84
- | 2.9881 | 17.0 | 663 | 1.5309 | 1.0 |
85
- | 2.9881 | 18.0 | 702 | 1.4300 | 0.9994 |
86
- | 2.9881 | 19.0 | 741 | 1.3280 | 0.9938 |
87
- | 2.9881 | 20.0 | 780 | 1.3012 | 0.9842 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
 
90
  ### Framework versions
91
 
92
- - Transformers 4.39.1
93
- - Pytorch 2.2.1+cu121
94
  - Datasets 2.18.0
95
  - Tokenizers 0.15.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
 
6
  datasets:
7
  - xtreme_s
8
  metrics:
 
11
  - name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod9
12
  results:
13
  - task:
 
14
  name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
  dataset:
17
  name: xtreme_s
18
  type: xtreme_s
 
20
  split: test
21
  args: fleurs.id_id
22
  metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.8831761712318515
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the xtreme_s dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.6655
36
+ - Wer: 0.8832
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 100
62
+ - num_epochs: 50
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer |
68
  |:-------------:|:-----:|:----:|:---------------:|:------:|
69
+ | 9.2247 | 1.0 | 39 | 3.1705 | 1.0 |
70
+ | 2.9516 | 2.0 | 78 | 2.8732 | 1.0 |
71
+ | 2.8953 | 3.0 | 117 | 2.8663 | 1.0 |
72
+ | 2.8878 | 4.0 | 156 | 2.8693 | 1.0 |
73
+ | 2.8818 | 5.0 | 195 | 2.8656 | 1.0 |
74
+ | 2.8814 | 6.0 | 234 | 2.8478 | 1.0 |
75
+ | 2.8817 | 7.0 | 273 | 2.8603 | 1.0 |
76
+ | 2.8771 | 8.0 | 312 | 2.8647 | 1.0 |
77
+ | 2.8811 | 9.0 | 351 | 2.8630 | 1.0 |
78
+ | 2.8703 | 10.0 | 390 | 2.8667 | 1.0 |
79
+ | 2.8608 | 11.0 | 429 | 2.8429 | 1.0 |
80
+ | 2.8578 | 12.0 | 468 | 2.8399 | 1.0 |
81
+ | 2.856 | 13.0 | 507 | 2.8531 | 1.0 |
82
+ | 2.8438 | 14.0 | 546 | 2.7872 | 1.0 |
83
+ | 2.7833 | 15.0 | 585 | 2.7015 | 1.0 |
84
+ | 2.7126 | 16.0 | 624 | 2.5606 | 1.0 |
85
+ | 2.4797 | 17.0 | 663 | 2.2529 | 1.0 |
86
+ | 2.2495 | 18.0 | 702 | 2.1600 | 1.0 |
87
+ | 1.8737 | 19.0 | 741 | 1.6194 | 1.0 |
88
+ | 1.69 | 20.0 | 780 | 1.4995 | 0.9999 |
89
+ | 1.5018 | 21.0 | 819 | 1.3398 | 0.9834 |
90
+ | 1.3264 | 22.0 | 858 | 1.2688 | 0.9692 |
91
+ | 1.1944 | 23.0 | 897 | 1.2211 | 0.9585 |
92
+ | 1.1186 | 24.0 | 936 | 1.1754 | 0.9517 |
93
+ | 1.0038 | 25.0 | 975 | 1.2082 | 0.9758 |
94
+ | 0.9096 | 26.0 | 1014 | 1.1463 | 0.9210 |
95
+ | 0.7954 | 27.0 | 1053 | 1.1530 | 0.9184 |
96
+ | 0.7337 | 28.0 | 1092 | 1.1948 | 0.9208 |
97
+ | 0.6438 | 29.0 | 1131 | 1.1907 | 0.9021 |
98
+ | 0.5933 | 30.0 | 1170 | 1.1994 | 0.9032 |
99
+ | 0.5646 | 31.0 | 1209 | 1.2765 | 0.9019 |
100
+ | 0.5314 | 32.0 | 1248 | 1.3331 | 0.9387 |
101
+ | 0.4208 | 33.0 | 1287 | 1.4003 | 0.9271 |
102
+ | 0.3769 | 34.0 | 1326 | 1.4226 | 0.9635 |
103
+ | 0.425 | 35.0 | 1365 | 1.3948 | 0.8890 |
104
+ | 0.3446 | 36.0 | 1404 | 1.4492 | 0.8901 |
105
+ | 0.3411 | 37.0 | 1443 | 1.5271 | 0.9136 |
106
+ | 0.3147 | 38.0 | 1482 | 1.4801 | 0.9139 |
107
+ | 0.2843 | 39.0 | 1521 | 1.5223 | 0.9011 |
108
+ | 0.2908 | 40.0 | 1560 | 1.6087 | 0.8871 |
109
+ | 0.2816 | 41.0 | 1599 | 1.5167 | 0.9097 |
110
+ | 0.2586 | 42.0 | 1638 | 1.5968 | 0.9129 |
111
+ | 0.2428 | 43.0 | 1677 | 1.6335 | 0.9100 |
112
+ | 0.2569 | 44.0 | 1716 | 1.5888 | 0.8967 |
113
+ | 0.2119 | 45.0 | 1755 | 1.6366 | 0.8910 |
114
+ | 0.2496 | 46.0 | 1794 | 1.6392 | 0.8807 |
115
+ | 0.2246 | 47.0 | 1833 | 1.6780 | 0.9197 |
116
+ | 0.2231 | 48.0 | 1872 | 1.7074 | 0.8969 |
117
+ | 0.2083 | 49.0 | 1911 | 1.6566 | 0.8811 |
118
+ | 0.2091 | 50.0 | 1950 | 1.6655 | 0.8832 |
119
 
120
 
121
  ### Framework versions
122
 
123
+ - Transformers 4.39.2
124
+ - Pytorch 2.2.2+cu121
125
  - Datasets 2.18.0
126
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca39c250fdd2b90b7a6aae3556180686e0bde43f53f7ad463e76e2c35f12e668
3
  size 1261975580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137d2e17807fe1ef671d8420af15cddcb7d4552fa4272566222a5787e1954c88
3
  size 1261975580
runs/Mar30_17-02-06_c69b10fbdf16/events.out.tfevents.1711818161.c69b10fbdf16.5538.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e07afb7ccd71eee2f10f30601e7c073199f954c2c3c10365cb2703cbeaa6c393
3
- size 26469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf3096b1486e9ef020edf53cabe7578ae2c7777894056a9275a754ca616b743
3
+ size 33171