sanchit-gandhi/distil-large-v3-hi-ft

distil-whisper/distil-large-v3

This model is a fine-tuned version of distil-whisper/distil-large-v3 on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6148
• Wer: 0.3298

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• 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
0.125	4.5	1000	0.4658	0.4300
0.0412	9.01	2000	0.5247	0.3960
0.0077	13.51	3000	0.5476	0.3535
0.0007	18.02	4000	0.5731	0.3398
0.0001	22.52	5000	0.6148	0.3298

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.1