whisper-medium-seiching – AI Model by seiching | AlphaNeural AI

You can deploy this model and start earning money today!

seiching/
whisper-medium-seiching

like

0

automatic-speech-recognition

generated_from_trainer

mozilla-foundation/common_voice_13_0

endpoints_compatible

Views

No views yet

Whisper medium zh - seiching

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

Loss: 0.2083
Wer Ortho: 37.9482
Wer: 37.6922

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.1472	0.69	500	0.1579	36.6425	36.4544
0.0545	1.38	1000	0.1685	37.4093	37.4725
0.0227	2.06	1500	0.1751	37.5544	37.9118
0.0262	2.75	2000	0.1885	37.9689	37.4925
0.0203	3.44	2500	0.2042	37.2228	36.7938
0.0123	4.13	3000	0.2065	38.3834	37.9916
0.0121	4.81	3500	0.2065	37.6373	37.7720
0.0151	5.5	4000	0.2083	37.9482	37.6922

Framework versions

Transformers 4.30.2
Pytorch 1.13.1+cu117
Datasets 2.13.2
Tokenizers 0.13.3