đ wav2vec2-large-xls-r-300m-bas-v1
This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - BAS dataset. It is designed for automatic speech recognition tasks and offers robust performance on relevant datasets.
⨠Features
- Language Support: Supports the Basaa (bas) language.
- Fine - Tuned Model: Based on the pre - trained
facebook/wav2vec2-xls-r-300m model, fine - tuned on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - BAS dataset.
- Performance Metrics: Achieves specific WER and CER scores on evaluation sets, indicating its effectiveness in speech recognition.
đĻ Installation
No 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
Evaluation Commands
- To evaluate on
mozilla - foundation/common_voice_8_0 with test split
python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-bas-v1 --dataset mozilla-foundation/common_voice_8_0 --config bas --split test --log_outputs
- To evaluate on
speech - recognition - community - v2/dev_data
Basaa (bas) language isn't available in speech - recognition - community - v2/dev_data
Training hyperparameters
The following hyperparameters were used during training:
| Property |
Details |
| learning_rate |
0.000111 |
| 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 |
500 |
| num_epochs |
100 |
| mixed_precision_training |
Native AMP |
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Wer |
| 12.7076 |
5.26 |
200 |
3.6361 |
1.0 |
| 3.1657 |
10.52 |
400 |
3.0101 |
1.0 |
| 2.3987 |
15.78 |
600 |
0.9125 |
0.6774 |
| 1.0079 |
21.05 |
800 |
0.6477 |
0.5352 |
| 0.7392 |
26.31 |
1000 |
0.5432 |
0.4929 |
| 0.6114 |
31.57 |
1200 |
0.5498 |
0.4639 |
| 0.5222 |
36.83 |
1400 |
0.5220 |
0.4561 |
| 0.4648 |
42.1 |
1600 |
0.5586 |
0.4289 |
| 0.4103 |
47.36 |
1800 |
0.5337 |
0.4082 |
| 0.3692 |
52.62 |
2000 |
0.5421 |
0.3861 |
| 0.3403 |
57.88 |
2200 |
0.5549 |
0.4096 |
| 0.3011 |
63.16 |
2400 |
0.5833 |
0.3925 |
| 0.2932 |
68.42 |
2600 |
0.5674 |
0.3815 |
| 0.2696 |
73.68 |
2800 |
0.5734 |
0.3889 |
| 0.2496 |
78.94 |
3000 |
0.5968 |
0.3985 |
| 0.2289 |
84.21 |
3200 |
0.5888 |
0.3893 |
| 0.2091 |
89.47 |
3400 |
0.5849 |
0.3852 |
| 0.2005 |
94.73 |
3600 |
0.5938 |
0.3875 |
| 0.1876 |
99.99 |
3800 |
0.5997 |
0.3870 |
Framework versions
- Transformers 4.16.1
- Pytorch 1.10.0+cu111
- Datasets 1.18.2
- Tokenizers 0.11.0
đ§ Technical Details
This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - BAS dataset. It is used for automatic speech recognition tasks. During training, specific hyperparameters were set, and the model was evaluated on different datasets to obtain performance metrics such as WER and CER.
đ License
The model is released 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)
