Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
repo_name – AI Model by wskang | AlphaNeural AI
You can deploy this model and start earning money today!
wskang
/
repo_name
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
hf-asr-leaderboard
generated_from_trainer
ko
wskang
openai/whisper-base
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper_fine_tune
This model is a fine-tuned version of
openai/whisper-base
on the datasets dataset. It achieves the following results on the evaluation set:
Loss: 0.6111
Cer: 17.7039
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: 8
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: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Cer
0.0311
10.0
1000
0.5066
70.4511
0.0018
20.0
2000
0.5717
19.3912
0.0009
30.0
3000
0.6002
17.7887
0.0007
40.0
4000
0.6111
17.7039
Framework versions
Transformers 4.50.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0
