Wav2vec2 Urdu

🚀 wav2vec2-large-xls-r-300m-Urdu

This model is a fine - tuned version of the base model, which can be used for automatic speech recognition. It addresses the challenge of Urdu speech recognition by fine - tuning on the common_voice dataset, providing more accurate recognition results.

🚀 Quick Start

This model is a fine - tuned version of Harveenchadha/vakyansh-wav2vec2-urdu-urm-60 on the common_voice dataset. It achieves the following results on the evaluation set:

• Wer: 0.5747
• Cer: 0.3268

✨ Features

• Automatic Speech Recognition: Specialized for Urdu speech recognition.
• Fine - Tuned Model: Based on the Harveenchadha/vakyansh-wav2vec2-urdu-urm-60 base model, fine - tuned on the common_voice dataset.

📚 Documentation

Model description

The training and valid dataset is 0.58 hours. It was hard to train any model on a lower number of samples, so the author decided to take the vakyansh-wav2vec2-urdu-urm-60 checkpoint and finetune the wav2vec2 model.

Training procedure

Trained on Harveenchadha/vakyansh-wav2vec2-urdu-urm-60 due to the lesser number of samples.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 64
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• 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: 100
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.16.0.dev0
• Pytorch 1.10.1+cu102
• Datasets 1.17.1.dev0
• Tokenizers 0.11.0

📄 License

This project is licensed under the Apache - 2.0 license.