SOTAVerified

Text to Speech

import gTTS import os def text_to_speech_kurdish(text, output_file="output.mp3"): # گۆڕینی نووسین بۆ دەنگ بە زمانی کوردی (هەڵبژاردنی زمانی "ku" بۆ کوردی) tts = gTTS(text=text, lang='ku', slow=False) tts.save(output_file) os.system(f"start {output_file}") # کردنەوەی فایلە دەنگییەکە (لە Windows) # نموونە: text_to_speech_kurdish("سڵاو، ئەمە دەنگی منە بە زمانی کوردی.")

Papers

Showing 10211030 of 1419 papers

TitleStatusHype
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech GenerationCode1
Reinforce-Aligner: Reinforcement Alignment Search for Robust End-to-End Text-to-Speech0
An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis0
Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis0
Dual Script E2E framework for Multilingual and Code-Switching ASR0
A Corpus of Neutral Voice Speech in Brazilian Portuguese0
Grad-TTS: A Diffusion Probabilistic Model for Text-to-SpeechCode1
Wav2KWS: Transfer Learning from Speech Representations for Keyword SpottingCode1
Learning Robust Latent Representations for Controllable Speech Synthesis0
DiffSinger: Singing Voice Synthesis via Shallow Diffusion MechanismCode2
Show:102550
← PrevPage 103 of 142Next →

No leaderboard results yet.