Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-tiny-en-US – AI Model by thuyentruong | AlphaNeural AI
You can deploy this model and start earning money today!
thuyentruong
/
whisper-tiny-en-US
like
0
tensorboard
safetensors
whisper
generated_from_trainer
automatic-speech-recognition
en
PolyAI/minds14
openai/whisper-tiny
finetune
apache-2.0
model-index
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper tiny
This model is a fine-tuned version of
openai/whisper-tiny
on the minds14 dataset. It achieves the following results on the evaluation set:
Loss: 0.6491
Wer Ortho: 0.3572
Wer: 0.3613
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-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 8
training_steps: 45
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer Ortho
Wer
0.0569
0.2679
15
0.6113
0.3337
0.3294
0.0364
0.5357
30
0.6443
0.3603
0.3554
0.0916
0.8036
45
0.6491
0.3572
0.3613
Framework versions
Transformers 4.40.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1
