Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-tiny-lg – AI Model by akera | AlphaNeural AI
You can deploy this model and start earning money today!
akera
/
whisper-tiny-lg
like
0
transformers
pytorch
whisper
automatic-speech-recognition
generated_from_trainer
common_voice_6_0
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-tiny-lg
This model is a fine-tuned version of
openai/whisper-tiny
on the common_voice_6_0 dataset. It achieves the following results on the evaluation set:
eval_loss: 2.0726
eval_wer: 228.8298
eval_runtime: 246.146
eval_samples_per_second: 2.84
eval_steps_per_second: 0.179
epoch: 41.67
step: 1000
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: 32
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
training_steps: 10000
mixed_precision_training: Native AMP
Framework versions
Transformers 4.27.0.dev0
Pytorch 1.11.0
Datasets 2.9.0
Tokenizers 0.13.2
