anuragshas/whisper-large-v2-hi-v3

Whisper Large-v2 Hindi

This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 hi dataset. It achieves the following results on the evaluation set:

• Loss: 0.3191
• Wer: 11.3039

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• 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: 50
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0479	2.06	200	0.2189	12.3226
0.0081	5.06	400	0.2649	11.5740
0.001	8.06	600	0.2998	11.4252
0.0004	11.05	800	0.3191	11.3039
0.0003	14.05	1000	0.3267	11.3291

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2