speecht5_finetuned_common_voice_17_0_mr
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: 0.5241
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.6254 | 16.0962 | 1000 | 0.5405 |
| 4.489 | 32.1924 | 2000 | 0.5284 |
| 4.4293 | 48.2886 | 3000 | 0.5270 |
| 4.3461 | 64.3848 | 4000 | 0.5241 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.0+cpu
- Datasets 3.0.3.dev0
- Tokenizers 0.20.1
- Downloads last month
- 73
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for VijayChoudhari/speecht5_finetuned_common_voice_17_0_mr
Base model
microsoft/speecht5_tts