đ wav2vec2-large-xls-r-300m-hindi
This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA - FOUNDATION/COMMON_VOICE_7_0 - HI dataset. It offers solutions for automatic speech recognition tasks and provides reliable performance on the evaluation set.
đ Quick Start
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - HI dataset.
It achieves the following results on the evaluation set:
đ Documentation
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 7.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 100.0
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Wer |
| 4.6095 |
3.38 |
500 |
4.5881 |
0.9999 |
| 3.3396 |
6.76 |
1000 |
3.3301 |
1.0001 |
| 2.0061 |
10.14 |
1500 |
1.2096 |
1.0063 |
| 1.523 |
13.51 |
2000 |
0.7836 |
1.0051 |
| 1.3868 |
16.89 |
2500 |
0.6837 |
1.0080 |
| 1.2807 |
20.27 |
3000 |
0.6568 |
1.0112 |
| 1.231 |
23.65 |
3500 |
0.6120 |
1.0105 |
| 1.1673 |
27.03 |
4000 |
0.5972 |
1.0089 |
| 1.1416 |
30.41 |
4500 |
0.5780 |
1.0132 |
| 1.0738 |
33.78 |
5000 |
0.5806 |
1.0123 |
| 1.0771 |
37.16 |
5500 |
0.5586 |
1.0067 |
| 1.0287 |
40.54 |
6000 |
0.5464 |
1.0058 |
| 1.0106 |
43.92 |
6500 |
0.5407 |
1.0062 |
| 0.9538 |
47.3 |
7000 |
0.5334 |
1.0089 |
| 0.9607 |
50.68 |
7500 |
0.5395 |
1.0110 |
| 0.9108 |
54.05 |
8000 |
0.5502 |
1.0137 |
| 0.9252 |
57.43 |
8500 |
0.5498 |
1.0062 |
| 0.8943 |
60.81 |
9000 |
0.5448 |
1.0158 |
| 0.8728 |
64.19 |
9500 |
0.5257 |
1.0113 |
| 0.8577 |
67.57 |
10000 |
0.5550 |
1.0178 |
| 0.8332 |
70.95 |
10500 |
0.5607 |
1.0166 |
| 0.8174 |
74.32 |
11000 |
0.5429 |
1.0145 |
| 0.8168 |
77.7 |
11500 |
0.5561 |
1.0116 |
| 0.7872 |
81.08 |
12000 |
0.5478 |
1.0164 |
| 0.7707 |
84.46 |
12500 |
0.5412 |
1.0216 |
| 0.7742 |
87.84 |
13000 |
0.5391 |
1.0207 |
| 0.7594 |
91.22 |
13500 |
0.5379 |
1.0208 |
| 0.7678 |
94.59 |
14000 |
0.5415 |
1.0198 |
| 0.7502 |
97.97 |
14500 |
0.5409 |
1.0191 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0
đ License
This model is licensed under the Apache - 2.0 license.
đ Model Index
| Property |
Details |
| Model Name |
XLS - R - 300M - Hindi |
| Task |
Automatic Speech Recognition |
| Dataset |
Common Voice 7 (mozilla - foundation/common_voice_7_0 - hi) |
| Test WER |
100 |
| Test CER |
92.98 |
đˇī¸ Tags
- automatic - speech - recognition
- generated_from_trainer
- hf - asr - leaderboard
- hi
- model_for_talk
- mozilla - foundation/common_voice_7_0
- robust - speech - event
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
