speecht5_tts_tr_v1.0 Open-source Model - Free conversion of Turkish text into natural speech

Home

Speecht5 Tts Tr V1.0

Developed by umarigan

A Turkish text-to-speech model fine-tuned from Microsoft SpeechT5, capable of generating natural speech

Speech Synthesis

Transformers

OtherOpen Source License:MIT #Turkish TTS #Speech Synthesis Fine-tuning #Multi-speaker Support

Downloads 959

Release Time : 9/23/2024

Model Overview

This model is a text-to-speech (TTS) model fine-tuned on Turkish voice datasets based on microsoft/speecht5_tts, capable of converting Turkish text into natural speech output

Model Features

High-Quality Speech Synthesis

Capable of generating natural and fluent Turkish speech

Speaker Embedding Support

Supports synthesis using specific speaker voice characteristics

Lightweight Fine-tuning

Efficient fine-tuning based on the pre-trained SpeechT5 model

Model Capabilities

Turkish text-to-speech

Specific speaker voice synthesis

Voice style conversion

Use Cases

Speech Synthesis Applications

Voice Assistants

Provides natural speech output for Turkish voice assistants

Audiobooks

Automatically converts Turkish text into speech

Assistive Technologies

Visual Impairment Assistance

Provides text-to-speech functionality for visually impaired users

🚀 SpeechT5 TTS Turkish

This model is a fine - tuned version of microsoft/speecht5_tts on the Turkish language, aiming to provide high - quality text - to - speech conversion.

🚀 Quick Start

Installation

!pip install datasets soundfile speechbrain

Inference

from transformers import pipeline
from datasets import load_dataset
import soundfile as sf
import torch
from IPython.display import Audio

synthesiser = pipeline("text-to-speech", "umarigan/speecht5_tts_tr_v1.0")

embeddings_dataset = load_dataset("umarigan/turkish_voice_dataset_embedded", split="train")
speaker_embedding = torch.tensor(embeddings_dataset[736]["speaker_embeddings"]).unsqueeze(0)

# Synthesize speech using the embedding
speech = synthesiser("Bir berber bir berbere gel beraber bir berber kuralım demiş", forward_params={"speaker_embeddings": speaker_embedding})

# Save the generated audio to a file
sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])

# Play the audio in the notebook
Audio("speech.wav")

✨ Features

This model is a fine - tuned version of microsoft/speecht5_tts on the turkishvoicedataset dataset. It achieves a loss of 0.3079 on the evaluation set.

📚 Documentation

Model Information

Property	Details
Model Name	SpeechT5 TTS Turkish
Base Model	microsoft/speecht5_tts
Model Type	Fine - tuned text - to - speech model
Training Datasets	erenfazlioglu/turkishvoicedataset
License	MIT

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: 6000
mixed_precision_training: Native AMP

Training Results

Training Loss	Epoch	Step	Validation Loss
0.4436	1.8484	1000	0.3752
0.3822	3.6969	2000	0.3403
0.3729	5.5453	3000	0.3233
0.3451	7.3937	4000	0.3153
0.3315	9.2421	5000	0.3099
0.3492	11.0906	6000	0.3079

Framework Versions

Transformers 4.45.0.dev0
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1

📄 License

This model is licensed under the MIT license.

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