wav2vec2-commonvoice-hindi

This model is a fine-tuned version of theainerd/Wav2Vec2-large-xlsr-hindi on the common_voice dataset. It achieves the following results on the evaluation set:

• Loss: 0.9825
• Wer: 0.6763

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: 16
• eval_batch_size: 8
• seed: 42
• 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	20.0	100	0.8801	0.6754

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.0+cu111
• Datasets 1.18.3
• Tokenizers 0.10.3