Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.
☆900Updated this week
Alternatives and similar repositories for Fun-ASR
Users that are interested in Fun-ASR are comparing it to the libraries listed below
Sorting:
- Open-Ended Speaking Style Modeling via Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training☆64Feb 7, 2026Updated 3 weeks ago
- Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.☆72Jan 14, 2026Updated last month
- CTC decoder with hotwords for ASR.☆34Apr 13, 2025Updated 10 months ago
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,774Updated this week
- MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows☆124Sep 2, 2025Updated 6 months ago
- GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters☆746Feb 12, 2026Updated 2 weeks ago
- Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation…☆1,345Feb 13, 2026Updated 2 weeks ago
- A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp.☆225Aug 6, 2025Updated 6 months ago
- Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music…☆1,688Jan 30, 2026Updated last month
- X-Talk is an open-source full-duplex cascaded spoken dialogue system framework enabling low-latency, interruptible, and human-like speech…☆178Updated this week
- FireRedASR2S is a SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandari…☆273Updated this week
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆110May 20, 2025Updated 9 months ago
- Multilingual Voice Understanding Model☆7,550Dec 30, 2025Updated 2 months ago
- A TTS Trained on Universal Audio.☆41Jun 6, 2025Updated 8 months ago
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆859Dec 2, 2025Updated 3 months ago
- ✨✨[NeurIPS 2025] VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model☆673May 24, 2025Updated 9 months ago
- [NeurIPS' 25] Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆189Dec 9, 2025Updated 2 months ago
- The baselines of ARC-Challenge-Interspeech2026☆56Dec 1, 2025Updated 3 months ago
- Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.☆878Updated this week
- ☆107Oct 1, 2025Updated 5 months ago
- A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity…☆14,956Feb 4, 2026Updated 3 weeks ago
- A Fully Self-Hosted Solution for Full-Duplex Voice Interaction☆494Sep 28, 2025Updated 5 months ago
- Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations☆62Jan 16, 2025Updated last year
- SpeechJudge: Towards Human-Level Judgment for Speech Naturalness (https://arxiv.org/abs/2511.07931)☆63Dec 23, 2025Updated 2 months ago
- A Framework for Speech, Language, Audio, Music Processing with Large Language Model☆974Jan 15, 2026Updated last month
- ☆486May 6, 2025Updated 9 months ago
- Port of Funasr's Sense-voice model in C/C++☆520Dec 19, 2025Updated 2 months ago
- Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.☆19,695Feb 11, 2026Updated 2 weeks ago
- low-latency realtime ASR based on FireRedASR☆57Jul 8, 2025Updated 7 months ago
- MiMo-Audio: Audio Language Models are Few-Shot Learners☆969Sep 20, 2025Updated 5 months ago
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆242Updated this week
- 修复funasr中seaco-paraformer导出onnx后没有时间戳的bug☆24Sep 12, 2024Updated last year
- A 6-million Audio-Caption Paired Dataset Built with a LLMs and ALMs-based Automatic Pipeline☆196Dec 13, 2024Updated last year
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆696Nov 27, 2025Updated 3 months ago
- Official code for "Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis"☆108Dec 20, 2025Updated 2 months ago
- A simple implementation for improving CosyVoice2 by GRPO method☆32Oct 17, 2025Updated 4 months ago
- Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.☆190Nov 10, 2024Updated last year
- Torch Audio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆62Sep 5, 2025Updated 5 months ago
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆506Dec 22, 2025Updated 2 months ago