🚀 Akashpb13/Swahili_xlsr
This model is designed for automatic speech recognition, offering high - performance results in the Swahili language. It fine - tunes a pre - trained model on specific datasets, achieving excellent performance on evaluation metrics.
✨ Features
- Fine - tuned Model: It's a fine - tuned version of [facebook/wav2vec2 - xls - r - 300m](https://huggingface.co/facebook/wav2vec2 - xls - r - 300m) on the MOZILLA - FOUNDATION/COMMON_VOICE_7_0 - hu dataset.
- High - quality Results: Achieves low WER (Word Error Rate) and CER (Character Error Rate) on evaluation sets.
📦 Installation
No installation steps are provided in the original document, so this section is skipped.
📚 Documentation
Model description
"facebook/wav2vec2 - xls - r - 300m" was finetuned.
Intended uses & limitations
More information needed
Training and evaluation data
- Training data: Common voice Hausa train.tsv and dev.tsv. Only those points were considered where upvotes were greater than downvotes and duplicates were removed after concatenation of all the datasets given in common voice 7.0
Training procedure
For creating the training dataset, all possible datasets were appended and a 90 - 10 split was used.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.000096
- train_batch_size: 16
- eval_batch_size: 16
- seed: 13
- gradient_accumulation_steps: 2
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 500
- num_epochs: 80
- mixed_precision_training: Native AMP
Training results
| Step |
Training Loss |
Validation Loss |
Wer |
| 500 |
4.810000 |
2.168847 |
0.995747 |
| 1000 |
0.564200 |
0.209411 |
0.303485 |
| 1500 |
0.217700 |
0.153959 |
0.239534 |
| 2000 |
0.150700 |
0.139901 |
0.216327 |
| 2500 |
0.119400 |
0.137543 |
0.208828 |
| 3000 |
0.099500 |
0.140921 |
0.203045 |
| 3500 |
0.087100 |
0.138835 |
0.199649 |
| 4000 |
0.074600 |
0.141297 |
0.195844 |
| 4500 |
0.066600 |
0.148560 |
0.194127 |
| 5000 |
0.060400 |
0.151214 |
0.194388 |
| 5500 |
0.054400 |
0.156072 |
0.192187 |
| 6000 |
0.051100 |
0.154726 |
0.190322 |
| 6500 |
0.048200 |
0.159847 |
0.189538 |
| 7000 |
0.046400 |
0.158727 |
0.188307 |
| 7500 |
0.046500 |
0.159032 |
0.187934 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.0+cu102
- Datasets 1.18.3
- Tokenizers 0.10.3
Evaluation Commands
- To evaluate on
mozilla - foundation/common_voice_8_0 with split test
python eval.py --model_id Akashpb13/Swahili_xlsr --dataset mozilla - foundation/common_voice_8_0 --config sw --split test
📄 License
This model is released under the Apache 2.0 license.
Model Information Table
| Property |
Details |
| Model Type |
Fine - tuned version of facebook/wav2vec2 - xls - r - 300m |
| Training Data |
Common voice Hausa train.tsv and dev.tsv (with specific filtering) |
| Datasets |
mozilla - foundation/common_voice_8_0 |
| Languages |
sw |
| Tags |
automatic - speech - recognition, generated_from_trainer, hf - asr - leaderboard, model_for_talk, mozilla - foundation/common_voice_8_0, robust - speech - event, sw |
Model Index
| Task |
Dataset |
Metrics |
| Automatic Speech Recognition |
Common Voice 8 (mozilla - foundation/common_voice_8_0, args: sw) |
Test WER: 0.11763625454589981, Test CER: 0.02884228669922436 |
| Automatic Speech Recognition |
Robust Speech Event - Dev Data (speech - recognition - community - v2/dev_data, args: kmr) |
Test WER: 0.11763625454589981, Test CER: 0.02884228669922436 |
%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)
