OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.
☆495Nov 23, 2025Updated 6 months ago
Alternatives and similar repositories for OSUM
Users that are interested in OSUM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Massive Contextual Speech Recognition Benchmark.☆107Aug 6, 2025Updated 10 months ago
- We propose C2SER, a novel audio-language model designed to enhance the stability and accuracy of speech emotion recognition through conte…☆17Mar 3, 2025Updated last year
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆512Dec 22, 2025Updated 5 months ago
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆250Feb 25, 2026Updated 3 months ago
- A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows☆280Jan 8, 2026Updated 5 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- An instruct text-to-speech solution based on LLaSA and CosyVoice2 developed by the ASLP lab and collaborators.☆250Feb 26, 2026Updated 3 months ago
- A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp.☆230Apr 8, 2026Updated 2 months ago
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆47Mar 10, 2025Updated last year
- A Survey of Spoken Dialogue Models (60 pages)☆317Nov 28, 2024Updated last year
- A Framework for Speech, Language, Audio, Music Processing with Large Language Model☆1,035Jan 15, 2026Updated 4 months ago
- ✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM☆381May 27, 2025Updated last year
- Llasa Speed Up☆63Jan 18, 2026Updated 4 months ago
- A song aesthetic evaluation toolkit trained on SongEval.☆307Apr 8, 2026Updated 2 months ago
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction☆221Feb 28, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆104Apr 1, 2025Updated last year
- The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.☆192Feb 28, 2026Updated 3 months ago
- A Large-scale Wu Dialect Speech Corpus with Multi-dimensional Annotations☆149Feb 6, 2026Updated 4 months ago
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,899Feb 25, 2026Updated 3 months ago
- We Speech Toolkit, LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction☆207Apr 7, 2026Updated 2 months ago
- Audio-FLAN☆161Sep 23, 2025Updated 8 months ago
- Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆357Jul 21, 2025Updated 10 months ago
- The official repository for the paper “NonVerbalSpeech-38K: A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understandi…☆66Dec 26, 2025Updated 5 months ago
- Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications☆92Dec 20, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"☆374Sep 3, 2024Updated last year
- Audio Codec Speech processing Universal PERformance Benchmark☆306May 5, 2026Updated last month
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆115Dec 2, 2025Updated 6 months ago
- Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations☆66Jan 16, 2025Updated last year
- Inference code for Audiodec-Valle-Wenetspeech4TTS☆51Jul 14, 2024Updated last year
- Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"☆217Sep 19, 2024Updated last year
- We propose C2SER, a novel audio-language model designed to enhance the stability and accuracy of speech emotion recognition through conte…☆48Mar 3, 2025Updated last year
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆444Jan 25, 2024Updated 2 years ago
- Di♪♪Rhythm 2: Efficient And High Fidelity Song Generation Via Block Flow Matching☆164Nov 9, 2025Updated 7 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training fo…☆1,142Dec 23, 2024Updated last year
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆62Nov 1, 2024Updated last year
- The open source code for LLM-Codec☆147Aug 18, 2024Updated last year
- [NeurIPS 2025] Benchmark data and code for MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix☆212Feb 25, 2026Updated 3 months ago
- AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model☆304Oct 12, 2025Updated 7 months ago
- An neural full-band audio codec for general audio sampled at 48 kHz with 7.5 kps or 4.5 kbps.☆208Updated this week
- Target Speaker Extraction Toolkit☆276Oct 4, 2025Updated 8 months ago