Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mironshoh-whisper-medium-uz-10k – AI Model by Inomjonov | AlphaNeural AI
You can deploy this model and start earning money today!
Inomjonov
/
mironshoh-whisper-medium-uz-10k
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
uz
mozilla-foundation/common_voice_13_0
openai/whisper-medium
finetune
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Mironshoh whisper-medium 10k row data
This model is a fine-tuned version of
openai/whisper-medium
on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
Loss: 0.5526
Wer Ortho: 50.2959
Wer: 45.8091
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 500
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer Ortho
Wer
0.5422
0.8
500
0.5526
50.2959
45.8091
Framework versions
Transformers 4.48.2
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0
