---
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: zlm_b128_le4_s4000
  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. -->

# zlm_b128_le4_s4000

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: 0.3181

## 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.385         | 0.8377 | 500  | 0.3593          |
| 0.3735        | 1.6754 | 1000 | 0.3449          |
| 0.37          | 2.5131 | 1500 | 0.3446          |
| 0.366         | 3.3508 | 2000 | 0.3387          |
| 0.3576        | 4.1885 | 2500 | 0.3337          |
| 0.3561        | 5.0262 | 3000 | 0.3288          |
| 0.3482        | 5.8639 | 3500 | 0.3197          |
| 0.3469        | 6.7016 | 4000 | 0.3181          |


### Framework versions

- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1