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.
☆51Updated 9 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:
- Official implementation of the TTS model Lina-Speech☆170Updated 9 months ago
- RWKV-SpeechChat is a real-time dialogue script based on a frozen 3B RWKV model with trained adapters and initial states. Various trained …☆27Updated 9 months ago
- This project is to train an RWKV LLM for TTS generation which compatible to other TTS engine(like fish/cosy/chattts).☆85Updated this week
- A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.☆76Updated 11 months ago
- ☆99Updated last week
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆98Updated 4 months ago
- Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"☆117Updated 4 months ago
- LSLM implements full duplex modeling in interactive speech language models, based on research by Ma et al. (2024). This project advances …☆76Updated 3 months ago
- Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆159Updated 2 months ago
- Audio tokenization, in the fastest way possible!☆53Updated last year
- An unofficial PyTorch implementation of VALL-E☆88Updated 2 months ago
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆102Updated last year
- Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".☆25Updated last year
- This repository contains a series of works on diffusion-based speech tokenizers, including the official implementation of the paper: "TaD…☆183Updated 3 weeks ago
- Official Code for ParrotTTS☆55Updated 11 months ago
- flow mirror models from JZX AI Labs☆44Updated last year
- ☆57Updated last year
- OpenS2S : Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model☆84Updated 2 months ago
- Official release of StyleTalk dataset.☆70Updated last year
- （WIP）long form speech generatoins☆31Updated 6 months ago
- ☆29Updated 8 months ago
- Text-audio foundation model from Boson AI☆107Updated last month
- ☆22Updated 11 months ago
- A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.☆58Updated 11 months ago
- All generative model in one for better TTS model☆73Updated last year
- ☆50Updated 6 months ago
- A unified tokenizer that is capable of both extracting semantic information and enabling high-fidelity audio reconstruction.☆99Updated 3 weeks ago
- Python runtime for WeTextProcessing (does not depend on Pynini)☆32Updated this week
- Implementation of Google's USM speech model in Pytorch☆30Updated this week
- StyleTTS 2 Optimized Training Fork☆33Updated 8 months ago