nodlehs/whisper_finetune

Whisper Medium Hindi

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

• Loss: 0.2306
• Wer: 12.9819

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: 2
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.218	0.2	1000	0.2970	20.1538
0.1537	0.4	2000	0.2573	17.2535
0.0802	1.16	3000	0.2392	14.2798
0.0521	1.36	4000	0.2263	13.7144
0.0135	2.13	5000	0.2306	12.9819

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.9.0
• Tokenizers 0.13.2