---
library_name: transformers
language:
- bn
license: mit
base_model: microsoft/speecht5_tts
tags:
- Bengali
- generated_from_trainer
datasets:
- ucalyptus/train-bn
model-index:
- name: SpeechT5-tuned-bn
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# SpeechT5-tuned-bn

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the train-bn dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6115

## 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: 2
- 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: 200
- num_epochs: 3.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.9582        | 0.1805 | 100  | 0.8410          |
| 0.8427        | 0.3610 | 200  | 0.7400          |
| 0.7583        | 0.5415 | 300  | 0.6792          |
| 0.744         | 0.7220 | 400  | 0.6601          |
| 0.7088        | 0.9025 | 500  | 0.6473          |
| 0.6847        | 1.0830 | 600  | 0.6369          |
| 0.6921        | 1.2635 | 700  | 0.6359          |
| 0.7143        | 1.4440 | 800  | 0.6462          |
| 0.6815        | 1.6245 | 900  | 0.6241          |
| 0.6759        | 1.8051 | 1000 | 0.6203          |
| 0.6647        | 1.9856 | 1100 | 0.6171          |
| 0.6558        | 2.1661 | 1200 | 0.6183          |
| 0.6673        | 2.3466 | 1300 | 0.6138          |
| 0.6574        | 2.5271 | 1400 | 0.6135          |
| 0.649         | 2.7076 | 1500 | 0.6125          |
| 0.6546        | 2.8881 | 1600 | 0.6115          |


### Framework versions

- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1