---
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
model-index:
- name: speecht5_finetuned_nepali
  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_finetuned_nepali

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_11_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2102

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.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
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.1494        | 500.0  | 500  | 0.9763          |
| 0.0917        | 1000.0 | 1000 | 1.1197          |
| 0.0901        | 1500.0 | 1500 | 1.2297          |
| 0.095         | 2000.0 | 2000 | 1.2102          |


### Framework versions

- Transformers 4.53.1
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.2