---
library_name: transformers
language:
- bn
license: mit
base_model: microsoft/speecht5_tts
tags:
- Bengali
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
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 common_voice_17_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5359

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 5.8567        | 0.3410 | 100  | 0.6441          |
| 5.2397        | 0.6820 | 200  | 0.5953          |
| 4.9733        | 1.0230 | 300  | 0.5845          |
| 4.9026        | 1.3640 | 400  | 0.5642          |
| 4.7326        | 1.7050 | 500  | 0.5552          |
| 4.7213        | 2.0460 | 600  | 0.5523          |
| 4.7226        | 2.3870 | 700  | 0.5433          |
| 4.5556        | 2.7280 | 800  | 0.5359          |


### Framework versions

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