deepdml/whisper-base-mix-en

Whisper base mixed-English

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

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

It achieves the following results on the evaluation set:

• Loss: 0.5065
• Wer: 19.9389

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
0.2909	0.2	1000	0.5348	21.1519
0.2316	0.4	2000	0.5255	20.7474
0.2351	0.6	3000	0.5132	20.3192
0.1924	0.8	4000	0.5097	20.0584
0.1984	1.0	5000	0.5065	19.9389

Framework versions

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