ASLP-lab / OSUMLinks
OSUM: Open Speech Understanding Model, open-sourced by ASLP@NPU.
☆378Updated 3 weeks ago
Alternatives and similar repositories for OSUM
Users that are interested in OSUM are comparing it to the libraries listed below
Sorting:
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆368Updated 3 weeks ago
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction☆207Updated 5 months ago
- ☆285Updated 3 months ago
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆414Updated last year
- A Survey of Spoken Dialogue Models (60 pages)☆306Updated 8 months ago
- We Speech Transcript based on LLM, in 300 lines of code.☆174Updated last month
- Github repository for ACL 2025 paper: Recent Advances in Speech Language Models: A Survey.☆121Updated last month
- Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.☆175Updated 8 months ago
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆217Updated 6 months ago
- ☆201Updated 10 months ago
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆330Updated last week
- A toolkit for speaker diarization.☆233Updated last month
- 使用vllm加速cosyvoice2的推理☆375Updated 3 months ago
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆579Updated 2 weeks ago
- Unoffical implementation of Megatts2☆286Updated last year
- 🤗 R1-AQA Model: mispeech/r1-aqa☆281Updated 4 months ago
- Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3☆415Updated 10 months ago
- GPT-4o-level, real-time spoken dialogue system.☆348Updated 6 months ago
- Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation…☆316Updated last week
- VoiceBench: Benchmarking LLM-Based Voice Assistants☆259Updated 2 weeks ago
- An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement☆164Updated last month
- ✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM☆333Updated 2 months ago
- ☆446Updated 2 months ago
- Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)☆499Updated this week
- Update ASR paper everyday☆279Updated this week
- llama-omni训练代码复现☆66Updated 6 months ago
- ☆11Updated 7 months ago
- MOSS-TTSD is a spoken dialogue generation model that enables expressive dialogue speech synthesis in both Chinese and English, supporting…☆637Updated this week
- Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆284Updated last week
- ☆87Updated 2 months ago