MooreThreads / MooERLinks
MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction models along with training and inference code, covering but not limited to end-to-end speech interaction, end-to-end speech translation and speech recognition.
☆214Updated 6 months ago
Alternatives and similar repositories for MooER
Users that are interested in MooER are comparing it to the libraries listed below
Sorting:
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction☆202Updated 4 months ago
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆345Updated this week
- ✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM☆328Updated last month
- ☆201Updated 9 months ago
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆413Updated last year
- ☆270Updated 3 months ago
- 🤗 R1-AQA Model: mispeech/r1-aqa☆274Updated 3 months ago
- Unoffical implementation of Megatts2☆286Updated last year
- A Survey of Spoken Dialogue Models (60 pages)☆305Updated 7 months ago
- OSUM: Open Speech Understanding Model, open-sourced by ASLP@NPU.☆375Updated last week
- Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.☆174Updated 8 months ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆103Updated 3 months ago
- F5-TTS 推理加速,速度提升约4倍!☆100Updated 6 months ago
- An easy-to-use, fast, and easily integrable tool for evaluating audio LLM☆120Updated last week
- Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3☆413Updated 10 months ago
- ☆126Updated 2 months ago
- TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loud…☆100Updated 6 months ago
- 使用vllm加速cosyvoice2的推理☆369Updated 2 months ago
- ☆85Updated last month
- ☆21Updated 8 months ago
- We Speech Transcript based on LLM, in 300 lines of code.☆170Updated 3 weeks ago
- llama-omni训练代码复现☆65Updated 5 months ago
- MOSS-TTSD is a spoken dialogue generation model that enables expressive dialogue speech synthesis in both Chinese and English, supporting…☆353Updated last week
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆244Updated last week
- An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement☆160Updated 2 weeks ago
- [ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"☆351Updated 10 months ago
- Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆282Updated last month
- 基于语言学本体构建,全面覆盖汉语多音字、音变等现象的高效中文TTS数据集。A linguistically grounded and comprehensive Chinese TTS dataset, efficiently covering Chinese polyph…☆35Updated 11 months ago
- The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.☆158Updated 3 months ago
- flow mirror models from JZX AI Labs☆44Updated 9 months ago