whisper-tiny-zh_CN_cosine – AI Model by VingeNie | AlphaNeural AI

You can deploy this model and start earning money today!

VingeNie/
whisper-tiny-zh_CN_cosine

like

0

automatic-speech-recognition

generated_from_trainer

mozilla-foundation/common_voice_16_1

openai/whisper-tiny

endpoints_compatible

Views

No views yet

Whisper Tiny chinese - VingeNie

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

Loss: 1.0204
Cer Ortho: 48.2903
Cer: 37.8890

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-06
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: cosine
lr_scheduler_warmup_steps: 100
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer Ortho	Cer
2.027	0.1088	100	1.8566	58.8395	45.4613
1.0547	0.2176	200	1.0853	50.8309	39.8595
1.0003	0.3264	300	1.0360	47.7982	38.6397
0.9744	0.4353	400	1.0224	48.7018	38.0597
0.9318	0.5441	500	1.0204	48.2903	37.8890

Framework versions

Transformers 4.40.0
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1