deepdml/whisper-tiny-mix-en

Whisper tiny mixed-English

This model is a fine-tuned version of openai/whisper-tiny on the "en" datasets:

• mozilla-foundation/common_voice_17_0
• google/fleurs
• facebook/voxpopuli

It achieves the following results on the evaluation set:

• Loss: 0.6272
• Wer: 26.4827

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: 64
• eval_batch_size: 16
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3844	0.2	1000	0.6787	28.9037
0.3104	0.4	2000	0.6485	27.1148
0.3125	0.6	3000	0.6359	26.4310
0.2607	0.8	4000	0.6310	26.3389
0.2683	1.0	5000	0.6272	26.4827

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1