Hugging Face's logo

KasuleTrevor
/
wav2vec2-large-xls-r-300m-ln-BibleTTS-1hr-v1

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
KasuleTrevor commited on
Commit
d80bf5c
·
verified ·
1 Parent(s): dd38414

End of training

Browse files
Files changed (1) hide show
  1. README.md +98 -28
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
- base_model: facebook/wav2vec2-xls-r-300m
3
  license: apache-2.0
4
- metrics:
5
- - wer
6
  tags:
7
  - generated_from_trainer
 
 
8
  model-index:
9
  - name: wav2vec2-large-xls-r-300m-ln-BibleTTS-1hr-v1
10
  results: []
@@ -13,14 +13,14 @@ model-index:
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/ASR%20Africa/runs/8upd5mvp)
17
  # wav2vec2-large-xls-r-300m-ln-BibleTTS-1hr-v1
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 16.1633
22
- - Wer: 1.0
23
- - Cer: 0.9528
24
 
25
  ## Model description
26
 
@@ -55,27 +55,97 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
58
- | 17.52 | 0.9091 | 5 | 17.4583 | 1.0006 | 0.9329 |
59
- | 14.5883 | 2.0 | 11 | 17.4264 | 1.0 | 0.9406 |
60
- | 17.4551 | 2.9091 | 16 | 17.3503 | 1.0 | 0.9485 |
61
- | 14.4258 | 4.0 | 22 | 17.1566 | 1.0 | 0.9284 |
62
- | 17.0466 | 4.9091 | 27 | 17.0089 | 1.0064 | 0.8739 |
63
- | 13.8992 | 6.0 | 33 | 16.5181 | 1.0016 | 0.8602 |
64
- | 16.1308 | 6.9091 | 38 | 15.8983 | 1.0 | 0.9305 |
65
- | 12.7375 | 8.0 | 44 | 14.7465 | 1.0 | 0.9109 |
66
- | 14.097 | 8.9091 | 49 | 13.4125 | 1.0 | 0.9107 |
67
- | 10.278 | 10.0 | 55 | 11.2263 | 1.0 | 1.0 |
68
- | 10.3623 | 10.9091 | 60 | 9.6075 | 1.0 | 1.0 |
69
- | 7.1725 | 12.0 | 66 | 7.9180 | 1.0 | 1.0 |
70
- | 7.2214 | 12.9091 | 71 | 6.8677 | 1.0 | 1.0 |
71
- | 5.2238 | 14.0 | 77 | 5.9195 | 1.0 | 1.0 |
72
- | 5.6119 | 14.9091 | 82 | 5.3951 | 1.0 | 1.0 |
73
- | 4.3099 | 16.0 | 88 | 4.9045 | 1.0 | 1.0 |
74
- | 4.8564 | 16.9091 | 93 | 4.6202 | 1.0 | 1.0 |
75
- | 3.8605 | 18.0 | 99 | 4.3694 | 1.0 | 1.0 |
76
- | 4.4506 | 18.9091 | 104 | 4.2304 | 1.0 | 1.0 |
77
- | 3.5941 | 20.0 | 110 | 4.0793 | 1.0 | 1.0 |
78
- | 4.1995 | 20.9091 | 115 | 3.9925 | 1.0 | 1.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
 
1
  ---
 
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
 
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: wav2vec2-large-xls-r-300m-ln-BibleTTS-1hr-v1
10
  results: []
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/ASR%20Africa/runs/vpqq6bfx)
17
  # wav2vec2-large-xls-r-300m-ln-BibleTTS-1hr-v1
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6740
22
+ - Wer: 0.7140
23
+ - Cer: 0.1802
24
 
25
  ## Model description
26
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
58
+ | 17.416 | 0.9091 | 5 | 17.5456 | 1.0 | 1.5562 |
59
+ | 14.5068 | 2.0 | 11 | 17.5120 | 1.0 | 1.4789 |
60
+ | 17.3472 | 2.9091 | 16 | 17.4189 | 1.0 | 1.1780 |
61
+ | 14.3268 | 4.0 | 22 | 17.2016 | 1.0 | 0.9674 |
62
+ | 17.0088 | 4.9091 | 27 | 17.0130 | 1.0 | 1.0293 |
63
+ | 13.9609 | 6.0 | 33 | 16.7075 | 1.0 | 0.8481 |
64
+ | 16.4587 | 6.9091 | 38 | 16.4284 | 1.0 | 0.8363 |
65
+ | 13.3164 | 8.0 | 44 | 15.9681 | 1.0 | 0.9944 |
66
+ | 15.3216 | 8.9091 | 49 | 15.3243 | 1.0 | 1.0 |
67
+ | 11.5548 | 10.0 | 55 | 14.0370 | 1.0 | 1.0 |
68
+ | 11.5967 | 10.9091 | 60 | 12.5247 | 1.0 | 1.0 |
69
+ | 8.2049 | 12.0 | 66 | 11.1587 | 1.0 | 1.0 |
70
+ | 8.4152 | 12.9091 | 71 | 10.0872 | 1.0 | 1.0 |
71
+ | 6.0687 | 14.0 | 77 | 8.8445 | 1.0 | 1.0 |
72
+ | 6.4176 | 14.9091 | 82 | 8.1147 | 1.0 | 1.0 |
73
+ | 4.8424 | 16.0 | 88 | 7.4897 | 1.0 | 1.0 |
74
+ | 5.3723 | 16.9091 | 93 | 6.9360 | 1.0 | 1.0 |
75
+ | 4.1999 | 18.0 | 99 | 6.3607 | 1.0 | 1.0 |
76
+ | 4.7866 | 18.9091 | 104 | 5.9263 | 1.0 | 1.0 |
77
+ | 3.8236 | 20.0 | 110 | 5.5028 | 1.0 | 1.0 |
78
+ | 4.4302 | 20.9091 | 115 | 5.0334 | 1.0 | 1.0 |
79
+ | 3.591 | 22.0 | 121 | 4.6869 | 1.0 | 1.0 |
80
+ | 4.1949 | 22.9091 | 126 | 4.4762 | 1.0 | 1.0 |
81
+ | 3.4191 | 24.0 | 132 | 4.2646 | 1.0 | 1.0 |
82
+ | 4.0108 | 24.9091 | 137 | 4.1448 | 1.0 | 1.0 |
83
+ | 3.28 | 26.0 | 143 | 3.9637 | 1.0 | 1.0 |
84
+ | 3.8588 | 26.9091 | 148 | 3.8742 | 1.0 | 1.0 |
85
+ | 3.158 | 28.0 | 154 | 3.7669 | 1.0 | 1.0 |
86
+ | 3.7243 | 28.9091 | 159 | 3.7039 | 1.0 | 1.0 |
87
+ | 3.0502 | 30.0 | 165 | 3.5948 | 1.0 | 1.0 |
88
+ | 3.6 | 30.9091 | 170 | 3.5306 | 1.0 | 1.0 |
89
+ | 2.9515 | 32.0 | 176 | 3.4187 | 1.0 | 1.0 |
90
+ | 3.4903 | 32.9091 | 181 | 3.3450 | 1.0 | 1.0 |
91
+ | 2.8763 | 34.0 | 187 | 3.2715 | 1.0 | 1.0 |
92
+ | 3.3998 | 34.9091 | 192 | 3.2082 | 1.0 | 1.0 |
93
+ | 2.7964 | 36.0 | 198 | 3.2021 | 1.0 | 1.0 |
94
+ | 3.3113 | 36.9091 | 203 | 3.1217 | 1.0 | 1.0 |
95
+ | 2.7362 | 38.0 | 209 | 3.0453 | 1.0 | 1.0 |
96
+ | 3.2274 | 38.9091 | 214 | 3.0072 | 1.0 | 1.0 |
97
+ | 2.6544 | 40.0 | 220 | 2.9557 | 1.0 | 1.0 |
98
+ | 3.1479 | 40.9091 | 225 | 2.9229 | 1.0 | 1.0 |
99
+ | 2.5983 | 42.0 | 231 | 2.8882 | 1.0 | 1.0 |
100
+ | 3.0854 | 42.9091 | 236 | 2.8638 | 1.0 | 1.0 |
101
+ | 2.5509 | 44.0 | 242 | 2.8354 | 1.0 | 1.0 |
102
+ | 3.0388 | 44.9091 | 247 | 2.8169 | 1.0 | 1.0 |
103
+ | 2.517 | 46.0 | 253 | 2.8000 | 1.0 | 1.0 |
104
+ | 3.0042 | 46.9091 | 258 | 2.7845 | 1.0 | 1.0 |
105
+ | 2.4924 | 48.0 | 264 | 2.7746 | 1.0 | 1.0 |
106
+ | 2.9774 | 48.9091 | 269 | 2.7673 | 1.0 | 1.0 |
107
+ | 2.4696 | 50.0 | 275 | 2.7573 | 1.0 | 1.0 |
108
+ | 2.9528 | 50.9091 | 280 | 2.7507 | 1.0 | 1.0 |
109
+ | 2.4516 | 52.0 | 286 | 2.7300 | 1.0 | 1.0 |
110
+ | 2.9192 | 52.9091 | 291 | 2.7201 | 1.0 | 1.0 |
111
+ | 2.4026 | 54.0 | 297 | 2.6965 | 1.0 | 1.0 |
112
+ | 2.8441 | 54.9091 | 302 | 2.6793 | 1.0 | 1.0 |
113
+ | 2.3344 | 56.0 | 308 | 2.6544 | 1.0 | 1.0 |
114
+ | 2.7453 | 56.9091 | 313 | 2.6112 | 1.0 | 1.0 |
115
+ | 2.223 | 58.0 | 319 | 2.5443 | 1.0 | 1.0 |
116
+ | 2.5596 | 58.9091 | 324 | 2.4781 | 1.0 | 0.9985 |
117
+ | 2.0074 | 60.0 | 330 | 2.3645 | 1.0 | 0.8402 |
118
+ | 2.2236 | 60.9091 | 335 | 2.2414 | 1.0 | 0.7652 |
119
+ | 1.703 | 62.0 | 341 | 2.0875 | 1.0 | 0.6468 |
120
+ | 1.8108 | 62.9091 | 346 | 2.0012 | 1.0 | 0.6570 |
121
+ | 1.2854 | 64.0 | 352 | 1.7562 | 0.9994 | 0.5339 |
122
+ | 1.289 | 64.9091 | 357 | 1.5530 | 0.9984 | 0.4409 |
123
+ | 0.8914 | 66.0 | 363 | 1.5710 | 0.9998 | 0.5147 |
124
+ | 0.8887 | 66.9091 | 368 | 1.3824 | 0.9547 | 0.4007 |
125
+ | 0.6132 | 68.0 | 374 | 1.3746 | 0.9759 | 0.4337 |
126
+ | 0.6176 | 68.9091 | 379 | 1.2084 | 0.9326 | 0.3478 |
127
+ | 0.4483 | 70.0 | 385 | 1.3181 | 0.9215 | 0.3787 |
128
+ | 0.4877 | 70.9091 | 390 | 1.1160 | 0.8970 | 0.3005 |
129
+ | 0.3614 | 72.0 | 396 | 1.1371 | 0.9054 | 0.3223 |
130
+ | 0.3889 | 72.9091 | 401 | 1.0581 | 0.8344 | 0.2827 |
131
+ | 0.2835 | 74.0 | 407 | 0.8882 | 0.7899 | 0.2292 |
132
+ | 0.3203 | 74.9091 | 412 | 0.9902 | 0.8447 | 0.2651 |
133
+ | 0.2494 | 76.0 | 418 | 1.0597 | 0.8338 | 0.2928 |
134
+ | 0.2693 | 76.9091 | 423 | 0.9066 | 0.8115 | 0.2517 |
135
+ | 0.2094 | 78.0 | 429 | 0.8811 | 0.7823 | 0.2311 |
136
+ | 0.2332 | 78.9091 | 434 | 0.9556 | 0.8330 | 0.2648 |
137
+ | 0.1874 | 80.0 | 440 | 0.9001 | 0.8103 | 0.2374 |
138
+ | 0.2155 | 80.9091 | 445 | 0.9119 | 0.8338 | 0.2499 |
139
+ | 0.1691 | 82.0 | 451 | 0.8158 | 0.7254 | 0.2066 |
140
+ | 0.1941 | 82.9091 | 456 | 0.8922 | 0.8010 | 0.2407 |
141
+ | 0.1537 | 84.0 | 462 | 0.8880 | 0.8137 | 0.2343 |
142
+ | 0.1801 | 84.9091 | 467 | 0.8078 | 0.7503 | 0.2021 |
143
+ | 0.141 | 86.0 | 473 | 0.7358 | 0.7340 | 0.1920 |
144
+ | 0.161 | 86.9091 | 478 | 0.8496 | 0.7928 | 0.2307 |
145
+ | 0.1317 | 88.0 | 484 | 0.7789 | 0.7491 | 0.2017 |
146
+ | 0.1435 | 88.9091 | 489 | 0.9110 | 0.8074 | 0.2435 |
147
+ | 0.1168 | 90.0 | 495 | 0.7392 | 0.7249 | 0.1908 |
148
+ | 0.1223 | 90.9091 | 500 | 0.7573 | 0.7177 | 0.1904 |
149
 
150
 
151
  ### Framework versions