Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-medium-tamil – AI Model by kurianbenoy | AlphaNeural AI
You can deploy this model and start earning money today!
kurianbenoy
/
whisper-medium-tamil
like
0
transformers
pytorch
tensorboard
whisper
automatic-speech-recognition
whisper-event
hf-asr-leaderboard
generated_from_trainer
ta
mozilla-foundation/common_voice_11_0
10.57967/hf/0206
apache-2.0
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
This model is a fine-tuned version of
openai/whisper-medium
on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
Loss: 0.5735
Wer: 69.3194
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: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 2000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.0006
18.52
1000
0.5099
45.2989
0.0002
37.04
2000
0.5735
69.3194
Framework versions
Transformers 4.24.0
Pytorch 1.13.0+cu117
Datasets 2.7.1
Tokenizers 0.13.2
