xingchensong / TouchNetLinks
A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp.
☆216Updated 3 months ago
Alternatives and similar repositories for TouchNet
Users that are interested in TouchNet are comparing it to the libraries listed below
Sorting:
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆202Updated 3 months ago
- ☆147Updated 2 months ago
- We Speech Toolkit, LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction☆143Updated last week
- [NeurIPS' 25] Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆175Updated 3 weeks ago
- A Massive Contextual Speech Recognition Benchmark.☆96Updated 3 months ago
- A large-scale speech corpus introduced in Spark-TTS, built from diverse open-source datasets for training text-to-speech (TTS) systems.☆95Updated 6 months ago
- ☆103Updated last month
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction☆215Updated 8 months ago
- Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"☆126Updated 5 months ago
- A Survey of Spoken Dialogue Models (60 pages)☆310Updated 11 months ago
- ☆104Updated 3 weeks ago
- The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.☆173Updated 7 months ago
- Awesome Neural Codec Models, Text-to-Speech Synthesizers & Speech Language Models☆195Updated this week
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆102Updated 5 months ago
- Audio-FLAN☆160Updated last month
- An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement☆176Updated 2 months ago
- Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization☆188Updated last year
- VoiceBench: Benchmarking LLM-Based Voice Assistants☆298Updated 2 months ago
- Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.☆187Updated last year
- [NeurIPS 2025] Benchmark data and code for MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix☆176Updated 5 months ago
- An easy-to-use, fast, and easily integrable tool for evaluating audio LLM☆162Updated 2 weeks ago
- ☆100Updated last month
- TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loud…☆107Updated 10 months ago
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆208Updated last year
- This is an evolving repo for the paper "Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey".☆185Updated this week
- LUCY: Linguistic Understanding and Control Yielding Early Stage of Her☆56Updated 7 months ago
- Official code for "EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting"☆93Updated 3 weeks ago
- The open source code for LLM-Codec☆140Updated last year
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆434Updated 4 months ago
- [NeurIPS 2024] SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words☆53Updated last year