Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-base-en-puct-5k – AI Model by CheeLi03 | AlphaNeural AI
You can deploy this model and start earning money today!
CheeLi03
/
whisper-base-en-puct-5k
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
hf-asr-leaderboard
generated_from_trainer
en
fleurs
openai/whisper-base
finetune
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper Base English Punctuation 5k - Chee Li
This model is a fine-tuned version of
openai/whisper-base
on the Google Fleurs dataset. It achieves the following results on the evaluation set:
Loss: 0.6360
Wer: 19.8300
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 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: 5000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.0204
5.3191
1000
0.4849
18.1368
0.0018
10.6383
2000
0.5678
18.4225
0.0009
15.9574
3000
0.6035
19.2795
0.0006
21.2766
4000
0.6268
19.6210
0.0005
26.5957
5000
0.6360
19.8300
Framework versions
Transformers 4.46.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.20.3
