đ wav2vec2-large-xlsr-tamil-commonvoice
This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice dataset. It provides valuable capabilities for speech - related tasks and achieves the following results on the evaluation set:
đ Quick Start
This model can be quickly integrated into speech - related projects. You can use it based on the pre - trained model provided by Hugging Face.
⨠Features
- Fine - tuned on the common_voice dataset, which is suitable for Tamil speech tasks.
- Achieved specific loss and WER results on the evaluation set, indicating its effectiveness.
đĻ Installation
No specific installation steps are provided in the original document, so this section is skipped.
đģ Usage Examples
No code examples are provided in the original document, so this section is skipped.
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Wer |
| 12.0478 |
1.05 |
100 |
3.3867 |
1.0 |
| 3.2522 |
2.11 |
200 |
3.2770 |
1.0 |
| 3.1689 |
3.16 |
300 |
3.1135 |
1.0039 |
| 2.9278 |
4.21 |
400 |
2.0485 |
1.3109 |
| 1.3592 |
5.26 |
500 |
0.8044 |
1.0988 |
| 0.7472 |
6.32 |
600 |
0.6571 |
0.9474 |
| 0.5842 |
7.37 |
700 |
0.6079 |
0.9477 |
| 0.4831 |
8.42 |
800 |
0.6083 |
0.9491 |
| 0.4259 |
9.47 |
900 |
0.5916 |
0.8973 |
| 0.3817 |
10.53 |
1000 |
0.6070 |
0.9147 |
| 0.338 |
11.58 |
1100 |
0.5873 |
0.8617 |
| 0.3123 |
12.63 |
1200 |
0.5983 |
0.8844 |
| 0.287 |
13.68 |
1300 |
0.6146 |
0.8988 |
| 0.2706 |
14.74 |
1400 |
0.6068 |
0.8754 |
| 0.2505 |
15.79 |
1500 |
0.5996 |
0.8638 |
| 0.2412 |
16.84 |
1600 |
0.6106 |
0.8481 |
| 0.2176 |
17.89 |
1700 |
0.6152 |
0.8520 |
| 0.2255 |
18.95 |
1800 |
0.6150 |
0.8540 |
| 0.216 |
20.0 |
1900 |
0.6145 |
0.8512 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu102
- Datasets 1.13.3
- Tokenizers 0.10.3
đ License
This model is licensed under the Apache - 2.0 license.
%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)
