nvidia-china-sae / mair-hubView external linksLinks
☆80Dec 1, 2025Updated 2 months ago
Alternatives and similar repositories for mair-hub
Users that are interested in mair-hub are comparing it to the libraries listed below
Sorting:
- 5Hz Deep-Compression Speech VAE for AR-Diffusion and CALMs☆57Nov 19, 2025Updated 2 months ago
- [ICASSP 2026] Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis☆36Dec 24, 2025Updated last month
- An instruct text-to-speech solution based on LLaSA and CosyVoice2 developed by the ASLP lab and collaborators.☆220Jan 20, 2026Updated 3 weeks ago
- poorman's ar-dit tts☆45Dec 31, 2025Updated last month
- The open source code of ALMTokenizer2: Towards Low bit-rate and Semantic-rich Audio Tokenizer with Flow-based Scalar Diffusion Transforme…☆42Sep 5, 2025Updated 5 months ago
- An AR+AR TTS attempt.☆18Jan 13, 2025Updated last year
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆242Nov 11, 2025Updated 3 months ago
- Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations☆62Jan 16, 2025Updated last year
- Reimplementation of Miipher☆29Aug 16, 2023Updated 2 years ago
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆48Sep 4, 2023Updated 2 years ago
- Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion☆40Oct 22, 2022Updated 3 years ago
- Train the next generation of TTS systems.☆171Sep 13, 2024Updated last year
- Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"☆11Apr 10, 2025Updated 10 months ago
- T5Voice is a lightweight PyTorch implementation of T5-based text-to-speech synthesis, supporting both streaming and non-streaming speech …☆28Nov 7, 2025Updated 3 months ago
- A TTS Trained on Universal Audio.☆41Jun 6, 2025Updated 8 months ago
- A Large-scale Wu Dialect Speech Corpus with Multi-dimensional Annotations☆95Feb 6, 2026Updated last week
- Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"☆212Sep 19, 2024Updated last year
- This repository provides a multi-mode and multi-speaker expressive speech synthesis framework, including multi-attentive Tacotron, DurIAN…☆74Sep 21, 2022Updated 3 years ago
- Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆349Jul 21, 2025Updated 6 months ago
- Mandarin Chinese audio datasets aligned with Montreal Forced Aligner☆15Aug 13, 2024Updated last year
- ☆82Jan 22, 2025Updated last year
- Implementation of DCComix TTS: An End-to-End Expressive TTS with Discrete Code Collaborated with Mixer☆75Aug 21, 2023Updated 2 years ago
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆505Dec 22, 2025Updated last month
- MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, i…☆85Updated this week
- The baselines of ARC-Challenge-Interspeech2026☆56Dec 1, 2025Updated 2 months ago
- A simple implementation for improving CosyVoice2 by GRPO method☆32Oct 17, 2025Updated 4 months ago
- DUSTED: Spoken-Term Discovery using Discrete Speech Units☆18Oct 2, 2024Updated last year
- Official Repository of Paper: "SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding" (IC…☆64Jan 27, 2026Updated 3 weeks ago
- Official repository for the WenetSpeech-Chuan dataset.☆145Feb 5, 2026Updated last week
- FlowMirror-HydraVox — A natively accelerated multi-head autoregressive TTS system derived from CosyVoice 3.0. It predicts multiple tokens…☆38Feb 10, 2026Updated last week
- ☆14Aug 19, 2024Updated last year
- Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)☆608Feb 10, 2026Updated last week
- Descript Audio Codec - VAE Variant (.dac-vae): High-Fidelity Audio Compression with Variational Autoencoder☆31Aug 30, 2025Updated 5 months ago
- Compute WER and SER for speech recognition evaluation☆26Dec 15, 2025Updated 2 months ago
- ☆98Jan 19, 2026Updated 3 weeks ago
- Tidy Tunes is an easy-to-use pipeline for mining high-quality audio data for speech generation models. To do so, it chains multiple open …☆22Feb 7, 2026Updated last week
- ☆41Nov 4, 2025Updated 3 months ago
- GPT-style network for phonemization with durations of text☆68Mar 21, 2024Updated last year
- Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"☆149Jun 3, 2025Updated 8 months ago