Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-sanskrit-asr-model – AI Model by ekotaru | AlphaNeural AI
You can deploy this model and start earning money today!
ekotaru
/
whisper-sanskrit-asr-model
like
0
pytorch
tensorboard
whisper
generated_from_trainer
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-sanskrit-asr-model
This model is a fine-tuned version of
openai/whisper-small
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.2299
Wer: 1.0
Cer: 1.0
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: 8
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 5
num_epochs: 5
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
Cer
0.7277
1.0
70
0.5042
2.7339
2.0537
0.3391
2.0
140
0.3873
2.5505
2.4385
0.2061
3.0
210
0.2786
1.0
1.0
0.0813
4.0
280
0.2293
1.0
1.0
0.0502
5.0
350
0.2299
1.0
1.0
Framework versions
Transformers 4.26.1
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.13.3
