Wav2vec2 Large Xlsr Hindi Commonvoice

🚀 wav2vec2-large-xlsr-hindi_commonvoice

This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice dataset, which can be used for speech - related tasks.

🚀 Quick Start

This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice dataset. It achieves the following results on the evaluation set:

• Loss: 3.5947
• Wer: 1.0

✨ Features

This model is fine - tuned on the common_voice dataset, which may have better performance on speech - related tasks in the corresponding language environment.

📚 Documentation

Model description

More information needed

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.0+cu102
• Datasets 1.13.3
• Tokenizers 0.10.3

📄 License

This model is licensed under the Apache 2.0 license.