---
language:
- as
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- madhabpaul/assamese_tts_dataset
model-index:
- name: SpeechT5 TTS Assamese
  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 TTS Assamese

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Assamese TTS Dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4490

## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5553        | 16.0  | 200  | 0.4852          |
| 0.5026        | 32.0  | 400  | 0.4547          |
| 0.4595        | 48.0  | 600  | 0.4444          |
| 0.464         | 64.0  | 800  | 0.4472          |
| 0.4612        | 80.0  | 1000 | 0.4490          |


### Framework versions

- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1