đ Automatic Speech Recognition Model
This model is designed for automatic speech recognition, offering a solution to accurately transcribe spoken language into text. It is fine - tuned on specific datasets to achieve high performance in relevant tasks.
đ Quick Start
This model is a fine - tuned version of [facebook/wav2vec2 - xls - r - 1b](https://huggingface.co/facebook/wav2vec2 - xls - r - 1b) on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - JA dataset. It achieves the following results on the evaluation set:
- Loss: 0.5500
- Wer: 1.0132
- Cer: 0.1609
đĻ Installation
No installation steps are provided in the original document, so this section is skipped.
đģ Usage Examples
Evaluation Commands
- To evaluate on
mozilla - foundation/common_voice_8_0 with split test
python ./eval.py --model_id AndrewMcDowell/wav2vec2 - xls - r - 1b - japanese - hiragana - katakana --dataset mozilla - foundation/common_voice_8_0 --config ja --split test --log_outputs
- To evaluate on
mozilla - foundation/common_voice_8_0 with split test
python ./eval.py --model_id AndrewMcDowell/wav2vec2 - xls - r - 1b - japanese - hiragana - katakana --dataset speech - recognition - community - v2/dev_data --config de --split validation --chunk_length_s 5.0 --stride_length_s 1.0
đ Documentation
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
đ§ Technical Details
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 7.5e - 05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1500
- num_epochs: 50.0
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Wer |
Cer |
| 1.7019 |
12.65 |
1000 |
1.0510 |
0.9832 |
0.2589 |
| 1.6385 |
25.31 |
2000 |
0.6670 |
0.9915 |
0.1851 |
| 1.4344 |
37.97 |
3000 |
0.6183 |
1.0213 |
0.1797 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2.dev0
- Tokenizers 0.11.0
đ License
This project is licensed under the Apache - 2.0 license.
Additional Information
Tags
- automatic - speech - recognition
- mozilla - foundation/common_voice_8_0
- generated_from_trainer
- robust - speech - event
- ja
- hf - asr - leaderboard
Datasets
Model Index
| Task |
Dataset |
Metrics |
| Automatic Speech Recognition |
Common Voice 8 (type: mozilla - foundation/common_voice_8_0, args: ja) |
Test WER: 95.33, Test CER: 22.27 |
| Automatic Speech Recognition |
Robust Speech Event - Dev Data (type: speech - recognition - community - v2/dev_data, args: de) |
Test WER: 100.0, Test CER: 30.33 |
| Automatic Speech Recognition |
Robust Speech Event - Dev Data (type: speech - recognition - community - v2/dev_data, args: ja) |
Test CER: 29.63 |
| Automatic Speech Recognition |
Robust Speech Event - Test Data (type: speech - recognition - community - v2/eval_data, args: ja) |
Test CER: 32.69 |
%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)
