anuragshas/whisper-large-v2-ur

Whisper Large-v2 Urdu

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

• Loss: 0.5947
• Wer: 23.5021

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: 100
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1935	1.1	200	0.4241	29.6526
0.0649	3.09	400	0.4683	26.0622
0.0156	5.08	600	0.5444	25.8104
0.0039	7.08	800	0.5947	23.5021
0.0019	9.07	1000	0.6123	23.8933

Framework versions

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