Edit model card

Speect5-common-voice-Hindi

This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4619

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: 0.0001
  • train_batch_size: 4
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • 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: 100
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
5.2577 0.3442 100 0.5713
4.7919 0.6885 200 0.5288
4.4862 1.0327 300 0.5080
4.2187 1.3769 400 0.4920
4.1509 1.7212 500 0.4841
4.1573 2.0654 600 0.4809
4.0679 2.4096 700 0.4745
4.0088 2.7539 800 0.4671
3.9249 3.0981 900 0.4624
3.9106 3.4423 1000 0.4619

Framework versions

  • Transformers 4.46.0.dev0
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.2
  • Tokenizers 0.20.1
Downloads last month
33
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Solo448/Speect5-common-voice-Hindi

Finetuned
(747)
this model

Dataset used to train Solo448/Speect5-common-voice-Hindi

Space using Solo448/Speect5-common-voice-Hindi 1