Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
whisper-tiny-zh_CN_lr5 – AI Model by VingeNie | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
VingeNie
/
whisper-tiny-zh_CN_lr5
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
zh
mozilla-foundation/common_voice_16_1
openai/whisper-tiny
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
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: 0.7486
Cer Ortho: 54.2817
Cer: 29.8525
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: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 25
training_steps: 650
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Cer Ortho
Cer
0.8045
0.3594
225
0.8040
53.9956
31.6580
0.7595
0.7188
450
0.7486
54.2817
29.8525
Framework versions
Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1
