Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-tiny-minds14-en – AI Model by b-koopman | AlphaNeural AI
You can deploy this model and start earning money today!
b-koopman
/
whisper-tiny-minds14-en
like
0
transformers
pytorch
tensorboard
whisper
automatic-speech-recognition
generated_from_trainer
PolyAI/minds14
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-tiny-minds14-en
This model is a fine-tuned version of
openai/whisper-tiny
on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
eval_loss: 0.6529
eval_wer_ortho: 0.3621
eval_wer: 0.3418
eval_runtime: 22.2394
eval_samples_per_second: 5.081
eval_steps_per_second: 0.36
step: 0
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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 500
Framework versions
Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3