You can deploy this model and start earning money today!

dianavdavidson/
wh_med_cv_common_voices_52393__val_finetune_trial

Name: wh_med_cv_common_voices_52393__val_finetune_trial
Availability: InStock

transformers

safetensors

whisper

automatic-speech-recognition

generated_from_trainer

common_voice_22_0

openai/whisper-medium

finetune

apache-2.0

endpoints_compatible

Views

No views yet

wh_med_cv_common_voices_52393__val_finetune_trial

This model is a fine-tuned version of openai/whisper-medium on the common_voice_22_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.2130
Global Wer: 29.6643

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: 5e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Global Wer
0.8666	0.0411	50	0.7829	40.8717
0.3892	0.0821	100	0.3151	39.2041
0.2755	0.1232	150	0.2758	35.0677
0.2409	0.1642	200	0.2612	33.6831
0.2466	0.2053	250	0.2519	32.3116
0.1922	0.2463	300	0.2495	32.8689
0.2087	0.2874	350	0.2339	30.8355
0.2010	0.3284	400	0.2217	30.2347
0.2100	0.3695	450	0.2124	29.0068
0.1905	0.4105	500	0.2130	29.6643

Framework versions

Transformers 5.0.0.dev0
Pytorch 2.9.0+cu126
Datasets 3.6.0
Tokenizers 0.22.2

dianavdavidson/wh_med_cv_common_voices_52393__val_finetune_trial

wh_med_cv_common_voices_52393__val_finetune_trial

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

dianavdavidson/
wh_med_cv_common_voices_52393__val_finetune_trial