Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
deep-learning transformers artificial-intelligence attention-mechanism non-autoregressive audio-generation
-
Updated
Apr 24, 2025 - Python
#
non-autoregressive
Here are 35 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
StreamSpeech is an "All in One" seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
text-to-speech translation machine-translation voice speech tts speech-synthesis speech-recognition speech-to-text all-in-one speech-processing audio-processing asr streaming-audio seamless speech-enhancement speech-translation non-autoregressive text-to-audio simultaneous-translation
-
Updated
Jun 29, 2025 - Python
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
machine-learning text-to-speech deep-learning tts probabilistic tts-engines tts-api diffusion-model diffusion-models non-autoregressive probabilistic-machine-learning flow-matching
-
Updated
Oct 20, 2025 - Jupyter Notebook
PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech
text-to-speech deep-neural-networks pytorch tts speech-synthesis generative-model vae normalizing-flows high-quality neural-tts non-autoregressive fastspeech hifi-gan non-ar mel-gan portable-tts
-
Updated
Feb 17, 2022 - Python
PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
text-to-speech deep-neural-networks pytorch tts speech-synthesis gan generative-model diffusion diffusion-models neural-tts non-autoregressive fastspeech multi-speaker-tts hifi-gan ddpm non-ar diffspeech diffgan-tts single-speaker-tts
-
Updated
Feb 21, 2022 - Python
A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS
text-to-speech deep-learning unsupervised pytorch tts speech-synthesis transformer supervised multi-speaker sota comprehensive single-speaker neural-tts non-autoregressive fastspeech fastspeech2 hifi-gan non-ar mel-gan ultimate-tts
-
Updated
Sep 24, 2022 - Python
PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
text-to-speech tts speech-synthesis expressive-speech-synthesis non-autoregressive emotional-tts korean-tts expressive-tts emotional-speech-synthesis korean-speech-synthesis conversational-tts conversational-speech-synthesis
-
Updated
Aug 25, 2021 - Python
Official repository of DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech, ICASSP 2023
text-to-speech pytorch tts speech-synthesis dataset conversational-ai non-autoregressive conversational-data tts-dataset conversational-tts
-
Updated
Jun 5, 2025 - Python
PyTorch implementation of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (focused on DiffSpeech)
text-to-speech pytorch tts speech-synthesis english diffusion singing-voice diffusion-models neural-tts non-autoregressive fastspeech ddpm diffsinger
-
Updated
Feb 3, 2022 - Python
PyTorch Implementation of Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
text-to-speech style pytorch tts speech-synthesis english speaker prosody meta-learning one-shot speaker-adaptation neural-tts non-autoregressive fastspeech speech-style stylespeech meta-stylespeech unseen-speaker
-
Updated
Feb 10, 2022 - Python
PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
text-to-speech deep-neural-networks pytorch tts speech-synthesis generative-model semi-supervised-learning global-style-tokens neural-tts non-autoregressive parallel-tacotron non-ar emotion-transfer cross-speaker conditional-layer-normalization
-
Updated
Nov 9, 2022 - Python
PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
text-to-speech duration pytorch tts speech-synthesis english vae self-attention neural-tts non-autoregressive fastspeech parallel-tacotron parallel-tacotron2
-
Updated
Nov 18, 2021 - Python
[NeurIPS 2024] Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"
machine-learning natural-language-processing text-generation pytorch diffusion-models non-autoregressive mathematical-reasoning chain-of-thought-reasoning diffusion-lm
-
Updated
Mar 4, 2025 - Python
Paper Lists, Notes and Slides, Focus on NLP. For summarization, please refer to https://github.com/xcfcode/Summarization-Papers
nlp naacl notes presentation slides acl presentations conversation gan generation summarization emnlp knowledge-distillation data-augmentation aaai meta-learning graph-neural-networks gnn pretrain non-autoregressive
-
Updated
Jun 12, 2022
A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS
text-to-speech deep-learning unsupervised end-to-end pytorch tts speech-synthesis jets multi-speaker sota single-speaker neural-tts non-autoregressive fastspeech2 hifi-gan non-ar ultimate-tts text-to-wav
-
Updated
Jun 6, 2022 - Python
Reparameterized Discrete Diffusion Models for Text Generation
machine-learning natural-language-processing text-generation python3 pytorch language-model fairseq diffusion-models non-autoregressive
-
Updated
Feb 14, 2023 - Python
[AAAI 2024] GLOP: Learning Global Partition and Local Construction for Solving Large-scale Routing Problems in Real-time
reinforcement-learning deep-reinforcement-learning transformer vehicle-routing-problem hierarchical-reinforcement-learning divide-and-conquer travelling-salesman-problem neural-combinatorial-optimization autoregressive-neural-networks graph-neural-networks non-autoregressive capacitated-vehicle-routing-problem prize-collecting-travelling-salesman-problem
-
Updated
Jan 25, 2025 - Python
A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers ×ばつ speedup.
non-autoregressive simultaneous-translation speech-generation speech-to-speech-translation non-autoregressive-transformers
-
Updated
Oct 22, 2024 - Python
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
text-to-speech duration pytorch tts speech-synthesis vae unsupervised-learning glow self-attention neural-tts non-autoregressive transforer non-ar unsupervised-duration
-
Updated
Aug 3, 2021 - Python
PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
text-to-speech end-to-end pytorch tts speech-synthesis pitch timbre neural-tts non-autoregressive fastspeech pitch-control fastpitch
-
Updated
Aug 3, 2021 - Python
Improve this page
Add a description, image, and links to the non-autoregressive topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the non-autoregressive topic, visit your repo's landing page and select "manage topics."