🚀 wav2vec2-large-xls-r-300m-sat-final
This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - SAT dataset. It is designed for automatic speech recognition tasks, aiming to achieve high - quality speech - to - text conversion.
✨ Features
- Tags: automatic - speech - recognition, mozilla - foundation/common_voice_8_0, generated_from_trainer, sat, robust - speech - event, model_for_talk, hf - asr - leaderboard
- Datasets: mozilla - foundation/common_voice_8_0
📚 Documentation
Model Index
| Property |
Details |
| Model Name |
wav2vec2 - large - xls - r - 300m - sat - final |
| Task |
Automatic Speech Recognition |
| Dataset 1 |
Name: Common Voice 8, Type: mozilla - foundation/common_voice_8_0, Args: sat |
| Metrics 1 |
Test WER: 0.3493975903614458, Test CER: 0.13773314203730272 |
| Dataset 2 |
Name: Robust Speech Event - Dev Data, Type: speech - recognition - community - v2/dev_data, Args: sat |
| Metrics 2 |
Test WER: NA, Test CER: NA |
Evaluation Results
This model achieves the following results on the evaluation set:
Evaluation Commands
⚠️ Important Note
Santali (Ol Chiki) language not found in speech - recognition - community - v2/dev_data
Evaluate on mozilla - foundation/common_voice_8_0 with test split
python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-sat-final --dataset mozilla-foundation/common_voice_8_0 --config sat --split test --log_outputs
Evaluate on speech - recognition - community - v2/dev_data
python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-sat-final --dataset speech-recognition-community-v2/dev_data --config sat --split validation --chunk_length_s 10 --stride_length_s 1
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0004
- 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: 170
- num_epochs: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Wer |
| 10.6317 |
33.29 |
100 |
2.8629 |
1.0 |
| 2.047 |
66.57 |
200 |
0.9516 |
0.5703 |
| 0.4475 |
99.86 |
300 |
0.8539 |
0.3896 |
| 0.0716 |
133.29 |
400 |
0.8277 |
0.3454 |
| 0.047 |
166.57 |
500 |
0.7597 |
0.3655 |
| 0.0249 |
199.86 |
600 |
0.8012 |
0.3815 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0
📄 License
This 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)
