đ sammy786/wav2vec2-xlsr-romansh_sursilvan
This model is a fine - tuned version of facebook/wav2vec2-xls-r-1b on the rm - sursilv subset of the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 dataset, achieving specific performance metrics on the evaluation set.
đ Quick Start
This model is a fine - tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - rm - sursilv dataset.
It achieves the following results on the evaluation set (which is 10 percent of the train dataset merged with other and dev datasets):
⨠Features
Model description
"facebook/wav2vec2-xls-r-1b" was finetuned.
Intended uses & limitations
More information needed
đĻ Installation
No installation steps provided in the original document, so this section is skipped.
đģ Usage Examples
No code examples provided in the original document, so this section is skipped.
đ Documentation
Training and evaluation data
Training data -
Common voice Finnish train.tsv, dev.tsv and other.tsv
Training procedure
For creating the train dataset, all possible datasets were appended and a 90 - 10 split was used.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.000045637994662983496
- train_batch_size: 16
- eval_batch_size: 16
- seed: 13
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 500
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Step |
Training Loss |
Validation Loss |
Wer |
| 200 |
4.825500 |
2.932350 |
1.000000 |
| 400 |
1.325600 |
0.292645 |
0.415436 |
| 600 |
0.709800 |
0.219167 |
0.324451 |
| 800 |
0.576800 |
0.174390 |
0.275477 |
| 1000 |
0.538100 |
0.183737 |
0.272116 |
| 1200 |
0.475200 |
0.159078 |
0.253871 |
| 1400 |
0.420400 |
0.167277 |
0.240907 |
| 1600 |
0.393500 |
0.167216 |
0.247269 |
| 1800 |
0.407500 |
0.178282 |
0.239827 |
| 2000 |
0.374400 |
0.184590 |
0.239467 |
| 2200 |
0.382600 |
0.164106 |
0.227824 |
| 2400 |
0.363100 |
0.162543 |
0.228544 |
| 2600 |
0.199000 |
0.172903 |
0.231665 |
| 2800 |
0.150800 |
0.160117 |
0.222662 |
| 3000 |
0.101100 |
0.169553 |
0.222662 |
| 3200 |
0.104200 |
0.161056 |
0.220622 |
| 3400 |
0.096900 |
0.161562 |
0.216781 |
| 3600 |
0.092200 |
0.163880 |
0.212580 |
| 3800 |
0.089200 |
0.162288 |
0.214140 |
| 4000 |
0.076200 |
0.160470 |
0.213540 |
| 4200 |
0.087900 |
0.162827 |
0.213060 |
| 4400 |
0.066200 |
0.161096 |
0.213300 |
| 4600 |
0.076000 |
0.162060 |
0.213660 |
| 4800 |
0.071400 |
0.162045 |
0.213300 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.0+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.10.3
Evaluation Commands
- To evaluate on
mozilla - foundation/common_voice_8_0 with split test
python eval.py --model_id sammy786/wav2vec2-xlsr-romansh_sursilvan --dataset mozilla - foundation/common_voice_8_0 --config rm - sursilv --split test
đ§ Technical Details
The model is based on fine - tuning "facebook/wav2vec2-xls-r-1b" on the specific dataset. The training process involved appending all possible datasets and using a 90 - 10 split to create the training dataset. Specific hyperparameters were used during training, and the model's performance was evaluated on an evaluation set, achieving certain loss and WER values.
đ 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)
