metadata
library_name: transformers
language:
- hi
license: mit
base_model: microsoft/speecht5_tts
tags:
- Hindi
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
model-index:
- name: Speect5-common-voice-Hindi
results: []
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: 0.4646
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
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.3349 | 0.3442 | 100 | 0.5973 |
| 4.7257 | 0.6885 | 200 | 0.5412 |
| 4.3821 | 1.0327 | 300 | 0.5127 |
| 4.283 | 1.3769 | 400 | 0.4926 |
| 4.1735 | 1.7212 | 500 | 0.4865 |
| 4.0968 | 2.0654 | 600 | 0.4790 |
| 4.0861 | 2.4096 | 700 | 0.4687 |
| 3.9972 | 2.7539 | 800 | 0.4646 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1