24 results found Sort:

lucidrains
soundstorm-pytorch lucidrains
80
1.3k
mit
50
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
transformers deep-learning audio-generation non-autoregressive attention-mechanism artificial-intelligence
Created 2023-05-17
93 commits to main branch, last one 12 days ago
ictnlp
StreamSpeech ictnlp
66
883
mit
12
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
asr tts voice speech seamless all-in-one translation text-to-audio speech-to-text text-to-speech streaming-audio audio-processing speech-synthesis speech-processing non-autoregressive speech-enhancement speech-recognition speech-translation machine-translation simultaneous-translation
Created 2024-06-04
25 commits to main branch, last one about a month ago
shivammehta25
Matcha-TTS shivammehta25
80
636
mit
16
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
tts tts-api tts-engines deep-learning flow-matching probabilistic text-to-speech diffusion-model diffusion-models machine-learning non-autoregressive probabilistic-machine-learning
Created 2023-09-05
90 commits to main branch, last one about a month ago
keonlee9420
PortaSpeech keonlee9420
36
328
mit
20
PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech
tts vae non-ar mel-gan pytorch hifi-gan fastspeech neural-tts high-quality portable-tts text-to-speech generative-model speech-synthesis normalizing-flows non-autoregressive deep-neural-networks
Created 2021-10-06
16 commits to main branch, last one 2 years ago
keonlee9420
Comprehensive-Transformer-TTS keonlee9420
41
318
mit
12
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, aim...
tts sota non-ar mel-gan pytorch hifi-gan fastspeech neural-tts supervised fastspeech2 transformer ultimate-tts unsupervised comprehensive deep-learning multi-speaker single-speaker text-to-speech speech-synthesis non-autoregressive
Created 2021-08-24
10 commits to main branch, last one 2 years ago
keonlee9420
DiffGAN-TTS keonlee9420
44
310
mit
9
PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
gan tts ddpm non-ar pytorch hifi-gan diffusion diffspeech fastspeech neural-tts diffgan-tts text-to-speech diffusion-models generative-model speech-synthesis multi-speaker-tts non-autoregressive single-speaker-tts deep-neural-networks
Created 2022-02-14
3 commits to main branch, last one 2 years ago
keonlee9420
Expressive-FastSpeech2 keonlee9420
47
277
other
4
PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
tts korean-tts emotional-tts expressive-tts text-to-speech speech-synthesis conversational-tts non-autoregressive korean-speech-synthesis emotional-speech-synthesis expressive-speech-synthesis conversational-speech-synthesis
Created 2021-04-26
9 commits to main branch, last one 3 years ago
keonlee9420
DiffSinger keonlee9420
30
229
mit
4
PyTorch implementation of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (focused on DiffSpeech)
tts ddpm english pytorch diffusion diffsinger fastspeech neural-tts singing-voice text-to-speech diffusion-models speech-synthesis non-autoregressive
Created 2021-06-03
3 commits to main branch, last one 2 years ago
keonlee9420
DailyTalk keonlee9420
13
196
mit
7
Official repository of DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech, ICASSP 2023
tts dataset pytorch tts-dataset text-to-speech speech-synthesis conversational-ai conversational-tts non-autoregressive conversational-data
Created 2022-06-02
10 commits to main branch, last one about a year ago
keonlee9420
StyleSpeech keonlee9420
23
190
mit
6
PyTorch Implementation of Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
tts style english prosody pytorch speaker one-shot fastspeech neural-tts stylespeech speech-style meta-learning text-to-speech unseen-speaker meta-stylespeech speech-synthesis non-autoregressive speaker-adaptation
Created 2021-06-09
17 commits to main branch, last one 2 years ago
keonlee9420
Parallel-Tacotron2 keonlee9420
44
188
mit
13
PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
tts vae english pytorch duration fastspeech neural-tts self-attention text-to-speech speech-synthesis parallel-tacotron non-autoregressive parallel-tacotron2
Created 2021-04-30
5 commits to main branch, last one 3 years ago
keonlee9420
Cross-Speaker-Emotion-Transfer keonlee9420
26
181
mit
6
PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
tts non-ar pytorch neural-tts cross-speaker text-to-speech emotion-transfer generative-model speech-synthesis parallel-tacotron non-autoregressive global-style-tokens deep-neural-networks semi-supervised-learning conditional-layer-normalization
Created 2021-10-16
7 commits to main branch, last one about a year ago
xcfcode
What-I-Have-Read xcfcode
15
162
unknown
7
Paper Lists, Notes and Slides, Focus on NLP. For summarization, please refer to https://github.com/xcfcode/Summarization-Papers
acl gan gnn nlp aaai emnlp naacl notes slides pretrain generation conversation presentation meta-learning presentations summarization data-augmentation non-autoregressive graph-neural-networks knowledge-distillation
This repository has been archived (exclude archived)
Created 2019-06-05
124 commits to master branch, last one 2 years ago
keonlee9420
Comprehensive-E2E-TTS keonlee9420
19
143
unknown
11
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 ultimat...
tts jets sota non-ar pytorch hifi-gan end-to-end neural-tts fastspeech2 text-to-wav ultimate-tts unsupervised deep-learning multi-speaker single-speaker text-to-speech speech-synthesis non-autoregressive
Created 2022-03-30
4 commits to main branch, last one 2 years ago
HKUNLP
reparam-discrete-diffusion HKUNLP
3
90
apache-2.0
3
Reparameterized Discrete Diffusion Models for Text Generation
fairseq python3 pytorch language-model text-generation diffusion-models machine-learning non-autoregressive natural-language-processing
Created 2023-02-09
2 commits to main branch, last one about a year ago
keonlee9420
VAENAR-TTS keonlee9420
14
72
mit
4
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
tts vae glow non-ar pytorch duration neural-tts transforer self-attention text-to-speech speech-synthesis non-autoregressive unsupervised-duration unsupervised-learning
Created 2021-07-15
4 commits to main branch, last one 3 years ago
keonlee9420
FastPitchFormant keonlee9420
14
71
mit
2
PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
tts pitch timbre pytorch fastpitch end-to-end fastspeech neural-tts pitch-control text-to-speech speech-synthesis non-autoregressive
Created 2021-06-30
3 commits to main branch, last one 3 years ago
HKUNLP
diffusion-of-thoughts HKUNLP
2
67
unknown
8
Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"
pytorch diffusion-lm text-generation diffusion-models machine-learning non-autoregressive mathematical-reasoning chain-of-thought-reasoning natural-language-processing
Created 2024-02-12
3 commits to main branch, last one 7 months ago
keonlee9420
WaveGrad2 keonlee9420
16
66
mit
6
PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
tts audio robust pytorch duration synthesis end-to-end neural-tts text-to-audio score-matching text-to-speech speech-synthesis non-autoregressive phoneme-to-waveform
Created 2021-06-18
6 commits to main branch, last one 3 years ago
bearcatt
LaBERT bearcatt
12
66
unknown
6
A length-controllable and non-autoregressive image captioning model.
eccv2020 image-captioning non-autoregressive controllable-image-captioning
Created 2020-03-07
8 commits to master branch, last one 3 years ago
henry-yeh
GLOP henry-yeh
8
65
mit
2
[AAAI 2024] GLOP: Learning Global Partition and Local Construction for Solving Large-scale Routing Problems in Real-time
transformer divide-and-conquer non-autoregressive graph-neural-networks reinforcement-learning vehicle-routing-problem deep-reinforcement-learning travelling-salesman-problem autoregressive-neural-networks neural-combinatorial-optimization capacitated-vehicle-routing-problem hierarchical-reinforcement-learning prize-collecting-travelling-salesman-problem
Created 2022-09-13
135 commits to master branch, last one 2 months ago
ictnlp
NAST-S2x ictnlp
4
60
unknown
4
A fast speech-to-any translation model that supports simultaneous decoding and offers 28× speedup.
speech-generation non-autoregressive simultaneous-translation speech-to-speech-translation non-autoregressive-transformers
Created 2024-06-03
39 commits to main branch, last one about a month ago
keonlee9420
Daft-Exprt keonlee9420
13
56
mit
3
PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
tts style english prosody pytorch speaker neural-tts text-to-speech prosody-transfer speech-synthesis non-autoregressive gaussian-upsampling
Created 2021-08-09
6 commits to main branch, last one 2 years ago
hemingkx
SpecDec hemingkx
0
31
unknown
2
Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)
non-autoregressive speculative-decoding
Created 2022-03-31
41 commits to main branch, last one 9 months ago