Alternatives and similar repositories for Speculative-Sampling

Users that are interested in Speculative-Sampling are comparing it to the libraries listed below

• feifeibear / LLMSpeculativeSampling

  View on GitHub
  Fast inference from large lauguage models via speculative decoding
  ☆886Aug 22, 2024Updated last year
• revsic / torch-diffusion-wavegan

  View on GitHub
  Parallel waveform generation with DiffusionGAN
  ☆17Mar 26, 2022Updated 3 years ago
• d-matrix-ai / keyformer-llm

  View on GitHub
  Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning
  ☆58Mar 26, 2024Updated last year
• CODEJIN / MLPSinger

  View on GitHub
  ☆24Mar 15, 2022Updated 3 years ago
• hemingkx / SpeculativeDecodingPapers

  View on GitHub
  📰 Must-read papers and blogs on Speculative Decoding ⚡️
  ☆1,121Jan 24, 2026Updated 3 weeks ago
• samsad35 / code-ancogen

  View on GitHub
  [ICASSP 2025] AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder
  ☆12Mar 11, 2025Updated 11 months ago
• hanshounsu / d3rm

  View on GitHub
  ☆12Feb 3, 2026Updated last week
• sarulab-speech / multi-speaker-dgp

  View on GitHub
  Official implementation of DGP-based multi-speaker speech synthesis with PyTorch
  ☆24Mar 23, 2021Updated 4 years ago
• yoongi43 / VRVQ

  View on GitHub
  Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"
  ☆11Apr 10, 2025Updated 10 months ago
• FasterDecoding / Medusa

  View on GitHub
  Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
  ☆2,705Jun 25, 2024Updated last year
• zzw922cn / wesinger2

  View on GitHub
  Synthesized singing voice demos of WeSinger 2 paper.
  ☆26Feb 20, 2023Updated 2 years ago
• samsad35 / source-filter-vae

  View on GitHub
  [SpeechCom Journal] Learning and controlling the source-filter representation of speech with a variational autoencoder
  ☆45Apr 18, 2023Updated 2 years ago
• jasonppy / syllable-discovery

  View on GitHub
  Syllable Segmentation and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model
  ☆34Aug 27, 2023Updated 2 years ago
• FasterDecoding / REST

  View on GitHub
  REST: Retrieval-Based Speculative Decoding, NAACL 2024
  ☆214Sep 11, 2025Updated 5 months ago
• Infatoshi / MegaQwen

  View on GitHub
  Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)
  ☆70Updated this week
• thu-spmi / ST-NAS

  View on GitHub
  Efficient Neural Architecture Search via Straight-Through Gradients
  ☆13Nov 12, 2020Updated 5 years ago
• Kahsolt / TransTacoS-RetuneGAN

  View on GitHub
  A toy-like Text-to-Speech for Chinese/Mandarin synthesize, inspired by Tacotron & FastSpeech2 & RefineGAN.
  ☆15May 25, 2022Updated 3 years ago
• reppy4620 / vocoders

  View on GitHub
  My vocoder experiments
  ☆31Jul 26, 2025Updated 6 months ago
• haiciyang / LaDiffCodec

  View on GitHub
  ICASSP 2024 - Generative De-Quantization for Neural Speech Codec via Latent Diffusion.
  ☆55Nov 16, 2025Updated 2 months ago
• LiuXiaoxuanPKU / OSD

  View on GitHub
  ☆64Dec 3, 2024Updated last year
• mlvlab / CAF

  View on GitHub
  Official Implementation (Pytorch) of "Constant Acceleration Flow", NeurIPS 2024
  ☆35Oct 31, 2025Updated 3 months ago
• MLSpeech / FormantsTracker

  View on GitHub
  ☆12Apr 1, 2024Updated last year
• NEXTLab-ZJU / MelodyGLM

  View on GitHub
  ☆13Sep 1, 2023Updated 2 years ago
• redmist328 / APNet2

  View on GitHub
  Source code of APNet2, a vocoder
  ☆58Nov 23, 2023Updated 2 years ago
• RahulSChand / Weighted-low-rank-factorization-Pytorch

  View on GitHub
  PyTorch implementation of Language model compression with weighted low-rank factorization
  ☆13Jun 28, 2023Updated 2 years ago
• navi0105 / LyricAlignment

  View on GitHub
  Source code of paper "Adapting pretrained speech model for Mandarin lyrics transcription and alignment"
  ☆18Dec 14, 2023Updated 2 years ago
• hemingkx / Spec-Bench

  View on GitHub
  Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
  ☆367Apr 22, 2025Updated 9 months ago
• dilab-zju / self-speculative-decoding

  View on GitHub
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆214Feb 13, 2025Updated last year
• aqtq314 / VogenSVS

  View on GitHub
  ☆15Aug 22, 2025Updated 5 months ago
• VITA-Group / Q-Hitter

  View on GitHub
  ☆15Jun 4, 2024Updated last year
• AlexandaJerry / SingingVoice-MFA-Training

  View on GitHub
  MFA acoustic model training based on Opencpop
  ☆15Sep 23, 2022Updated 3 years ago
• Respaired / RiFornet_Vocoder

  View on GitHub
  a Neural Vocoder supporting Ring Attention, Conformer and NSF.
  ☆24Aug 1, 2025Updated 6 months ago
• liuhuang31 / g2pw_once

  View on GitHub
  G2pw's inference speed is accelerated by about 8-10 times. Change loop generated predictive data to only once and model loop prediction b…
  ☆14Dec 30, 2023Updated 2 years ago
• thuhcsi / SnakeGAN

  View on GitHub
  Please visit https://thuhcsi.github.io/SnakeGAN/
  ☆37Apr 25, 2023Updated 2 years ago
• xiangyue9607 / QVE

  View on GitHub
  Code for the ACL2022 paper "Synthetic Question Value Estimation for Domain Adaptation of Question Answering"
  ☆17Mar 21, 2022Updated 3 years ago
• xingchensong / CosyVoice-ttsfrd

  View on GitHub
  ☆25Jun 19, 2025Updated 7 months ago
• b04901014 / vae-gslm

  View on GitHub
  Official Implementation for the paper: A Variational Framework for Improving Naturalness in Generative Spoken Language Models
  ☆22Jun 18, 2025Updated 7 months ago
• mcf330 / efts2code

  View on GitHub
  source code of EfficientTTS 2
  ☆20Feb 18, 2024Updated last year
• huutuongtu / Lightvoc

  View on GitHub
  LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM
  ☆18May 17, 2024Updated last year