xiaomi-research / dasheng-lmLinks
Efficient audio understanding with general audio captions
☆355Updated last week
Alternatives and similar repositories for dasheng-lm
Users that are interested in dasheng-lm are comparing it to the libraries listed below
Sorting:
- OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.☆416Updated last week
- A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation☆139Updated last week
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆217Updated 8 months ago
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction☆207Updated 6 months ago
- ☆310Updated 5 months ago
- 🤗 R1-AQA Model: mispeech/r1-aqa☆298Updated 5 months ago
- Long-form streaming TTS system for multi-speaker dialogue generation☆90Updated last week
- ☆201Updated 11 months ago
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆580Updated 3 weeks ago
- Github repository for ACL 2025 paper: Recent Advances in Speech Language Models: A Survey.☆140Updated 3 months ago
- An easy-to-use, fast, and easily integrable tool for evaluating audio LLM☆140Updated last month
- ☆143Updated 3 weeks ago
- We Speech Transcript based on LLM, in 300 lines of code.☆176Updated 2 months ago
- Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.☆181Updated 10 months ago
- GPT-4o-level, real-time spoken dialogue system.☆354Updated 7 months ago
- Text-audio foundation model from Boson AI☆99Updated last week
- A Survey of Spoken Dialogue Models (60 pages)☆308Updated 9 months ago
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆158Updated last month
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆107Updated 5 months ago
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆425Updated last year
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆624Updated 2 months ago
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆404Updated 2 months ago
- 使用vllm加速cosyvoice2的推理☆413Updated 4 months ago
- ☆95Updated 2 weeks ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆112Updated 2 years ago
- ✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM☆341Updated 3 months ago
- a text-conditional diffusion probabilistic model capable of generating high fidelity audio.☆176Updated last year
- A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp.☆202Updated last month
- llama-omni训练代码复现☆69Updated 7 months ago
- TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loud…☆104Updated 8 months ago