wav2vec2-common_voice-en-demo

This model is a fine-tuned version of gagan3012/xls-r-300m-hi on the MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI dataset. It achieves the following results on the evaluation set:

• Loss: 3.5677
• Wer: 1.0

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: 2.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.69	100	18.5421	1.0
No log	1.38	200	3.9420	1.0

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.1.dev0
• Tokenizers 0.15.2