Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-medium-chinese-tw-minnan-soap-demucs-params-by-gpt – AI Model by TSukiLen | AlphaNeural AI
You can deploy this model and start earning money today!
TSukiLen
/
whisper-medium-chinese-tw-minnan-soap-demucs-params-by-gpt
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
openai/whisper-medium
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-medium-chinese-tw-minnan-soap-demucs-params-by-gpt
This model is a fine-tuned version of
openai/whisper-medium
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 2.1359
Wer: 165.8674
Cer: 95.8191
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: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 3000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
Cer
0.156
4.6512
1000
1.7188
134.4055
81.5125
0.0108
9.3023
2000
2.0146
176.8616
103.4110
0.0055
13.9535
3000
2.1359
165.8674
95.8191
Framework versions
Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1
