Wav2vec2 Large Xls R 300m Assamese

🚀 wav2vec2-large-xls-r-300m-assamese

This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_7_0 dataset. It offers significant value in the field of automatic speech recognition, providing a reliable solution for transcribing Assamese audio.

🚀 Quick Start

This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_7_0 dataset. It achieves the following results on the evaluation set:

• WER: 0.7954545454545454
• CER: 0.32341269841269843

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

To compute the evaluation parameters

cd wav2vec2-large-xls-r-300m-assamese; python eval.py --model_id ./ --dataset mozilla-foundation/common_voice_7_0 --config as --split test --log_outputs

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e - 4
• train_batch_size: 16
• eval_batch_size: 8
• seed: not given
• 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: 500
• num_epochs: 400
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.0+cu113
• Datasets 1.13.3
• Tokenizers 0.10.3

📄 License

This project is licensed under the Apache - 2.0 license.

📊 Model Index