---
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- tts
- generated_from_trainer
datasets:
- microsoft/speecht5_tts
model-index:
- name: SyedNaqi_TechSpeechT5_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. -->

# SyedNaqi_TechSpeechT5_TTS

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the TTS_English_data dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4244

## 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: 3e-05
- train_batch_size: 12
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1500
- training_steps: 3000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| No log        | 1.0     | 176  | 0.7486          |
| 0.9327        | 2.0     | 352  | 0.5466          |
| 0.6633        | 3.0     | 528  | 0.5009          |
| 0.6633        | 4.0     | 704  | 0.4828          |
| 0.5635        | 5.0     | 880  | 0.4694          |
| 0.5364        | 6.0     | 1056 | 0.4601          |
| 0.5364        | 7.0     | 1232 | 0.4609          |
| 0.5155        | 8.0     | 1408 | 0.4463          |
| 0.5025        | 9.0     | 1584 | 0.4459          |
| 0.4883        | 10.0    | 1760 | 0.4399          |
| 0.4883        | 11.0    | 1936 | 0.4342          |
| 0.4792        | 12.0    | 2112 | 0.4359          |
| 0.4715        | 13.0    | 2288 | 0.4264          |
| 0.4715        | 14.0    | 2464 | 0.4273          |
| 0.4646        | 15.0    | 2640 | 0.4238          |
| 0.4598        | 16.0    | 2816 | 0.4231          |
| 0.4598        | 17.0    | 2992 | 0.4227          |
| 0.452         | 17.0455 | 3000 | 0.4244          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1