Open-source Text-to-Speech Model speecht5_finetuned_emirhan_tr - Free Generation of High-quality Turkish Speech

Speecht5 Finetuned Emirhan Tr

Developed by emirhanbilgic

A Turkish text-to-speech model fine-tuned based on Microsoft SpeechT5, capable of generating high-quality Turkish speech.

Speech Synthesis

TensorBoard

OtherOpen Source License:MIT #Turkish TTS #High-quality speech synthesis #Transformer architecture

Downloads 22

Release Time : 8/27/2024

Model Overview

This model is a text-to-speech model fine-tuned on Turkish speech datasets based on Microsoft SpeechT5, specifically designed to generate natural and fluent Turkish speech.

Model Features

High-quality Turkish speech synthesis

Fine-tuned on Turkish speech datasets, capable of generating natural and fluent Turkish speech.

Transformer-based architecture

Utilizes the advanced SpeechT5 architecture to ensure the quality and efficiency of speech synthesis.

Easy integration

Provides a standard Hugging Face interface for easy integration into various applications.

Model Capabilities

Turkish text-to-speech

High-quality speech synthesis

Use Cases

Voice assistant

Turkish voice assistant

Provides voice interaction functionality for Turkish users

Generates natural and fluent Turkish responses

Accessibility tools

Text-to-speech tool

Provides Turkish text-to-speech functionality for visually impaired individuals

Accurately reads Turkish text content

Automatic announcement systems

Turkish information announcements

Used for automatic Turkish announcements in public transport and public spaces

Clear and accurate Turkish speech output

🚀 speecht5_finetuned_emirhan_tr

This model is a fine - tuned version of microsoft/speecht5_tts, designed to generate high - quality Turkish speech from text.

🚀 Quick Start

This model is a fine - tuned version of microsoft/speecht5_tts on erenfazlioglu/turkishvoicedataset. It achieves the following results on the evaluation set:

Loss: 0.3135

✨ Features

Model description

The base model uses a transformer - based approach, specifically Transfer Transformer, to generate high - quality speech from text. The fine - tuning process on the Turkish Voice Dataset enables the model to produce more natural and accurate speech in Turkish.

Intended uses & limitations

This model is intended for text - to - speech (TTS) applications specifically tailored for the Turkish language. It can be used in various scenarios, such as voice assistants, automated announcements, and accessibility tools for Turkish speakers. However, the model's performance is optimized for Turkish and may not generalize well to other languages. Also, it might not handle rare or domain - specific vocabulary as effectively as more common words.

📚 Documentation

Training and evaluation data

The model was fine - tuned on the Turkish Voice Dataset, which consists of high - quality synthetic Turkish voice recordings from Microsoft Azure. The dataset was split into training and evaluation subsets, with the evaluation set used to measure the model's loss and overall performance.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
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: 100
training_steps: 660
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.514	0.4545	100	0.4372
0.4226	0.9091	200	0.3626
0.3771	1.3636	300	0.3417
0.3562	1.8182	400	0.3278
0.3472	2.2727	500	0.3217
0.3402	2.7273	600	0.3135

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

📄 License

This model is released under the MIT license.

📦 Model Information

Property	Details
Model Type	Fine - tuned version of microsoft/speecht5_tts
Training Data	Turkish Voice Dataset from Microsoft Azure

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご