Xls R 300m Ur Cv8 Hi

🚀 Fine-tuned Speech Recognition Model

This model is a fine-tuned version of the speech recognition model, which aims to improve the accuracy and performance of automatic speech recognition on the Urdu language. It is based on the pre - trained model DrishtiSharma/wav2vec2-large-xls-r-300m-hi-d3 and fine - tuned on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - UR dataset.

🚀 Quick Start

This section provides a brief overview of the model's performance and key information.

Model Performance

It achieves the following results on the evaluation set:

• Loss: 1.5443
• Wer: 0.7030

📚 Documentation

Model description

This model is a fine - tuned version of DrishtiSharma/wav2vec2-large-xls-r-300m-hi-d3 on the MOZILLA - FOUNDATION/COMMON_VOICE_8_0 - UR dataset.

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.000388
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 750
• num_epochs: 100.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.3
• Tokenizers 0.11.0

📄 License

This model is licensed under the Apache - 2.0 license.