---
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_large_slr43
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ek-ghanti-services/speech_t5_nepali_large/runs/2jyasuds)
# speecht5_large_slr43

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: 0.4177

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 8000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch    | Step | Validation Loss |
|:-------------:|:--------:|:----:|:---------------:|
| 0.5161        | 17.2414  | 1000 | 0.4739          |
| 0.4913        | 34.4828  | 2000 | 0.4592          |
| 0.4883        | 51.7241  | 3000 | 0.4529          |
| 0.4713        | 68.9655  | 4000 | 0.4390          |
| 0.4561        | 86.2069  | 5000 | 0.4303          |
| 0.4538        | 103.4483 | 6000 | 0.4208          |
| 0.438         | 120.6897 | 7000 | 0.4186          |
| 0.4382        | 137.9310 | 8000 | 0.4177          |


### Framework versions

- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1