https://github.com/rwth-i6/returnn-experiments
공식 코드Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems
Papers with Code 아카이브
Text to Speech
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 2
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.")
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/sail-sg/mmcbench
공식 코드Benchmarking Large Multimodal Models against Common Corruptions
https://github.com/sarulab-speech/saslaw
공식 코드https://github.com/sbu-dsl/prosody-analysis-of-audiobooks
공식 코드https://github.com/sciforce/phones-las
공식 코드https://github.com/seongho608/ringformer
공식 코드RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer
https://github.com/sh-lee-prml/hierspeechpp
공식 코드https://github.com/sh-lee-prml/periodwave
공식 코드PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation
https://github.com/shark-nlp/attentivemlp
공식 코드Attentive Multi-Layer Perceptron for Non-autoregressive Generation
https://github.com/shinhyeokoh/rwen
공식 코드RWEN-TTS: Relation-aware Word Encoding Network for Natural Text-to-Speech Synthesis
https://github.com/shivammehta25/OverFlow
공식 코드OverFlow: Putting flows on top of neural transducers for better TTS
https://github.com/sislab-unitn/Let-s-Give-a-Voice-to-Conversational-Agents-in-VR
공식 코드Let's Give a Voice to Conversational Agents in Virtual Reality
https://github.com/soham97/pam
공식 코드PAM: Prompting Audio-Language Models for Audio Quality Assessment
https://github.com/sony/ai-research-code
공식 코드Towards Robust FastSpeech 2 by Modelling Residual Multimodality
https://github.com/sparkaudio/spark-tts
공식 코드Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
https://github.com/ssmlkl/mntts2
공식 코드MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset
https://github.com/suzhiba/Full-parallel_100x_real_time_End2EndTTS
공식 코드https://github.com/sweatybridge/text-to-anime
공식 코드https://github.com/takaaki-saeki/zm-text-tts
공식 코드https://github.com/talkingnow/HM-Conformer
공식 코드https://github.com/tensorflow/tensor2tensor
공식 코드On the Discrepancy between Density Estimation and Sequence Generation
https://github.com/theodorblackbird/lina-speech
공식 코드Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis
https://github.com/thudm/glm-4-voice
공식 코드GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot
https://github.com/thuhcsi/flattn
공식 코드An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer
https://github.com/thuhcsi/spanpsp
공식 코드A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
https://github.com/tianduowang/speech-bt
공식 코드From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition
https://github.com/tiberiu44/TTS-Cube
공식 코드https://github.com/tkc-morita/ZeroSpeech2020_TTSwoT
공식 코드https://github.com/tobuta/PolyGlotFake
공식 코드PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset
https://github.com/tonychenxyz/emoknob
공식 코드EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control
https://github.com/tts-tutorial/survey
공식 코드https://github.com/ttsds/ttsds
공식 코드https://github.com/ttslr/strengthnet
공식 코드Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learning
https://github.com/vinairesearch/xphonebert
공식 코드XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech
https://github.com/vita-mllm/vita-audio
공식 코드VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
https://github.com/vivian556123/neurips2024-covomix
공식 코드CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.