steja/whisper-large-sindhi

Whisper_large_Sindhi

This model is a fine-tuned version of anuragshas/whisper-large-v2-hi on the google/fleurs sd_in dataset. It achieves the following results on the evaluation set:

• Loss: 0.6382
• Wer: 27.6927

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: 8
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_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
0.0005	38.44	500	0.6382	27.6927
0.0003	76.89	1000	0.6714	27.8323

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2