Wav2vec2 Xls R Sl A1

🚀 wav2vec2-xls-r-sl-a1

This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - SL dataset. It is designed for automatic speech recognition tasks, providing valuable results on multiple datasets.

🚀 Quick Start

Evaluation Commands

1. To evaluate on mozilla - foundation/common_voice_8_0 with test split

python eval.py --model_id DrishtiSharma/wav2vec2-xls-r-sl-a1 --dataset mozilla-foundation/common_voice_8_0 --config sl --split test --log_outputs

2. To evaluate on speech - recognition - community - v2/dev_data

python eval.py --model_id DrishtiSharma/wav2vec2-xls-r-sl-a1 --dataset speech-recognition-community-v2/dev_data --config sl --split validation --chunk_length_s 10 --stride_length_s 1

✨ Features

• Fine - tuned Model: Based on facebook/wav2vec2-xls-r-300m, fine - tuned on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - SL dataset.
• Multiple Datasets Support: Achieves good results on datasets like Common Voice 8 and Robust Speech Event datasets.

📚 Documentation

Model Information

Model Performance

The model achieves the following results on different evaluation sets:

• Common Voice 8:
  • Test WER: 0.20626555409164105
  • Test CER: 0.051648321634392154
• Robust Speech Event - Dev Data:
  • Test WER: 0.5406156320830592
  • Test CER: 0.22249723590310583
• Robust Speech Event - Test Data:
  • Test WER: 55.24

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 7.1e - 05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 100.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.2.dev0
• Tokenizers 0.11.0

📄 License

This model is licensed under the apache - 2.0 license.