---
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: 0.5604

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.7779        | 0.1806 | 100  | 0.6979          |
| 0.6983        | 0.3613 | 200  | 0.6492          |
| 0.6825        | 0.5419 | 300  | 0.6292          |
| 0.6571        | 0.7225 | 400  | 0.6200          |
| 0.6536        | 0.9031 | 500  | 0.6150          |
| 0.6405        | 1.0838 | 600  | 0.6030          |
| 0.6319        | 1.2644 | 700  | 0.5925          |
| 0.6295        | 1.4450 | 800  | 0.5878          |
| 0.612         | 1.6256 | 900  | 0.5821          |
| 0.6129        | 1.8063 | 1000 | 0.5774          |
| 0.6155        | 1.9869 | 1100 | 0.5744          |
| 0.6056        | 2.1675 | 1200 | 0.5743          |
| 0.5957        | 2.3482 | 1300 | 0.5735          |
| 0.5928        | 2.5288 | 1400 | 0.5663          |
| 0.5974        | 2.7094 | 1500 | 0.5599          |
| 0.5927        | 2.8900 | 1600 | 0.5604          |


### Framework versions

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