AGENDD / RWKV-ASRLinks
This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the idea of SLAM_ASR and used the RWKV language model as the LLM, and instead of directly writing a prompt template we directly finetuned the initial state of the RWKV model.
☆50Updated 5 months ago
Alternatives and similar repositories for RWKV-ASR
Users that are interested in RWKV-ASR are comparing it to the libraries listed below
Sorting:
- RWKV-SpeechChat is a real-time dialogue script based on a frozen 3B RWKV model with trained adapters and initial states. Various trained …☆27Updated 5 months ago
- Official implementation of the TTS model Lina-Speech☆164Updated 4 months ago
- This project is to train an RWKV LLM for TTS generation which compatible to other TTS engine(like fish/cosy/chattts).☆75Updated this week
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆86Updated 2 weeks ago
- ☆124Updated this week
- ☆26Updated 3 months ago
- A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.☆69Updated 7 months ago
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆42Updated 2 weeks ago
- Official release of StyleTalk dataset.☆64Updated 11 months ago
- A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp/pp.☆67Updated last month
- flow mirror models from JZX AI Labs☆45Updated 8 months ago
- Implementation of Google's USM speech model in Pytorch☆30Updated last month
- Llasa Speed Up☆29Updated last week
- Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"☆38Updated this week
- 单独维护的中文TTS☆35Updated 2 years ago
- Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".☆24Updated 11 months ago
- This project is established for real-time training of the RWKV model.☆48Updated last year
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆98Updated 7 months ago
- ☆50Updated 2 months ago
- rwkv finetuning☆36Updated last year
- ☆13Updated last year
- AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension☆102Updated 5 months ago
- A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.☆52Updated 7 months ago
- An easy-to-use, fast, and easily integrable tool for evaluating audio LLM☆102Updated last week
- ☆26Updated 7 months ago
- All generative model in one for better TTS model☆71Updated 8 months ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆71Updated 7 months ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆93Updated 8 months ago
- An unofficial PyTorch implementation of VALL-E☆87Updated this week
- We introduce the LLAMA1 Test Set, a comprehensive open-domain world knowledge QA dataset for evaluating question-answering systems. We pr…☆18Updated last year