AGENDD / RWKV-ASR
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.
☆49Updated 4 months ago
Alternatives and similar repositories for RWKV-ASR:
Users that are interested in RWKV-ASR are comparing it to the libraries listed below
- RWKV-SpeechChat is a real-time dialogue script based on a frozen 3B RWKV model with trained adapters and initial states. Various trained …☆27Updated 4 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).☆73Updated 2 weeks ago
- ☆121Updated 3 weeks ago
- Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".☆24Updated 10 months ago
- flow mirror models from JZX AI Labs☆45Updated 7 months ago
- ☆91Updated last week
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆54Updated 2 weeks ago
- A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp/pp.☆62Updated 2 weeks ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆68Updated 6 months ago
- Just another FastSpeech 2 but cleaner code :)☆26Updated 10 months ago
- ☆13Updated 4 months ago
- [ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer☆52Updated 6 months ago
- Ke-Omni-R is an advanced audio reasoning model and achieved SOTA on MMAU☆12Updated last week
- ☆13Updated last year
- A low-bitrate single-codebook 16 kHz speech codec based on focal modulation☆86Updated 2 months ago
- Official Code for ParrotTTS☆50Updated 6 months ago
- ☆18Updated last year
- Inference code for Audiodec-Valle-Wenetspeech4TTS☆49Updated 9 months ago
- （WIP）long form speech generatoins☆31Updated last month
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated 8 months ago
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆39Updated last week
- A large-scale RWKV v6, v7(World, ARWKV, PRWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy o…☆35Updated this week
- rwkv finetuning☆36Updated last year
- An easy-to-use, fast, and easily integrable tool for evaluating audio LLM☆91Updated 3 weeks ago
- ☆26Updated 3 months ago
- We introduce the LLAMA1 Test Set, a comprehensive open-domain world knowledge QA dataset for evaluating question-answering systems. We pr…☆18Updated last year
- Chinese and English Bilinguish G2P☆21Updated last year
- All generative model in one for better TTS model☆67Updated 8 months ago
- ☆64Updated last year