A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp.
☆225Aug 6, 2025Updated 7 months ago
Alternatives and similar repositories for TouchNet
Users that are interested in TouchNet are comparing it to the libraries listed below
Sorting:
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆110May 20, 2025Updated 10 months ago
- ☆36Sep 6, 2025Updated 6 months ago
- We Speech Toolkit, LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction☆188Mar 9, 2026Updated last week
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆243Feb 25, 2026Updated 3 weeks ago
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆508Dec 22, 2025Updated 3 months ago
- （WIP）long form speech generatoins☆31Apr 2, 2025Updated 11 months ago
- Torch Audio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆61Sep 5, 2025Updated 6 months ago
- [NAACL 2025] WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching☆123Mar 27, 2025Updated 11 months ago
- Try to replicate the architecture of MiniMaxTTS mentioned in it's technical report☆48Sep 2, 2025Updated 6 months ago
- OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.☆482Nov 23, 2025Updated 3 months ago
- 5Hz Deep-Compression Speech VAE for AR-Diffusion and CALMs☆57Nov 19, 2025Updated 4 months ago
- We propose C2SER, a novel audio-language model designed to enhance the stability and accuracy of speech emotion recognition through conte…☆44Mar 3, 2025Updated last year
- Text-To-Speech for NotebookLM☆39Jul 20, 2025Updated 8 months ago
- faster inference☆28Jan 20, 2025Updated last year
- Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-Step High-Fidelity Audio Generation☆138Mar 8, 2026Updated 2 weeks ago
- A single-layer, streaming codec model providing SOTA audio quality and discrete tokens designed for superior downstream modelability.☆113Jun 4, 2025Updated 9 months ago
- Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations☆64Jan 16, 2025Updated last year
- Decoders from Kaldi using OpenFst☆34Jan 29, 2026Updated last month
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆114Dec 2, 2025Updated 3 months ago
- A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation☆282Feb 5, 2026Updated last month
- The official implementation of the DIFFA series for dLLM-based large audio language model☆68Mar 12, 2026Updated last week
- A Massive Contextual Speech Recognition Benchmark.☆104Aug 6, 2025Updated 7 months ago
- A unified tokenizer that is capable of both extracting semantic information and enabling high-fidelity audio reconstruction.☆133Sep 19, 2025Updated 6 months ago
- Descript Audio Codec - VAE Variant (.dac-vae): High-Fidelity Audio Compression with Variational Autoencoder☆35Aug 30, 2025Updated 6 months ago
- 🤗 R1-AQA Model: mispeech/r1-aqa☆317Mar 28, 2025Updated 11 months ago
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction☆219Feb 28, 2025Updated last year
- ☆23Oct 17, 2024Updated last year
- Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications☆90Dec 20, 2024Updated last year
- Real-time Speech-Text Foundation Model Toolkit (wip)☆254Mar 26, 2025Updated 11 months ago
- ACM MM 2024 FlashSpeech: Efficient Zero-Shot Speech Synthesis☆155Sep 20, 2024Updated last year
- A Framework for Speech, Language, Audio, Music Processing with Large Language Model☆1,011Jan 15, 2026Updated 2 months ago
- MiMo-Audio: Audio Language Models are Few-Shot Learners☆980Mar 3, 2026Updated 2 weeks ago
- poorman's ar-dit tts☆45Dec 31, 2025Updated 2 months ago
- We Speech Transcript based on LLM, in 300 lines of code.☆185Jun 20, 2025Updated 9 months ago
- The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.☆183Feb 28, 2026Updated 3 weeks ago
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆216Sep 10, 2024Updated last year
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆909Dec 2, 2025Updated 3 months ago
- A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/…☆396Updated this week
- Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation…☆1,371Mar 16, 2026Updated last week