Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
speecht5_tts_mal – AI Model by anirxudh | AlphaNeural AI
You can deploy this model and start earning money today!
anirxudh
/
speecht5_tts_mal
like
0
transformers
tensorboard
safetensors
speecht5
text-to-audio
generated_from_trainer
hi
mozilla-foundation/common_voice_17_0
microsoft/speecht5_tts
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
SpeechT5 hindi fine-tuning
This model is a fine-tuned version of
microsoft/speecht5_tts
on the CommonVoice dataset. It achieves the following results on the evaluation set:
Loss: 0.4338
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: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
training_steps: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
1.0775
7.5758
1000
0.4753
0.9791
15.1515
2000
0.4433
0.9368
22.7273
3000
0.4349
0.9392
30.3030
4000
0.4338
Framework versions
Transformers 4.47.0.dev0
Pytorch 2.5.0+cu121
Datasets 3.0.2
Tokenizers 0.20.1
