---
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: Bengali_finetuned_speecht5_tts
  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. -->

# Bengali_finetuned_speecht5_tts

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6190

## 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
- training_steps: 600
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 6.1441        | 1.9422  | 100  | 0.7127          |
| 5.5876        | 3.8988  | 200  | 0.6550          |
| 5.2451        | 5.8554  | 300  | 0.6514          |
| 5.1514        | 7.8120  | 400  | 0.6227          |
| 4.9727        | 9.7687  | 500  | 0.6220          |
| 4.9797        | 11.7253 | 600  | 0.6190          |


### Framework versions

- Transformers 4.46.0.dev0
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1