https://github.com/ms2ku-vtts/ms2ku-vtts
공식 코드Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.")
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech
Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis
PortaSpeech: Portable and High-Quality Generative Text-to-Speech
RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching
Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech
Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation
Systematic Inequalities in Language Technology Performance across the World's Languages
Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech
A Practical Guide to Logical Access Voice Presentation Attack Detection
Towards an AI to Win Ghana's National Science and Maths Quiz
Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS
Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
Phonological Features for 0-shot Multilingual Speech Synthesis
Naturalization of Text by the Insertion of Pauses and Filler Words
LibriS2S: A German-English Speech-to-Speech Translation Corpus
Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition
fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise Distillation
Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation
RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.