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.
☆54Dec 23, 2024Updated last year
Alternatives and similar repositories for RWKV-ASR
Users that are interested in RWKV-ASR are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- RWKV-SpeechChat is a real-time dialogue script based on a frozen 3B RWKV model with trained adapters and initial states. Various trained …☆29Jan 1, 2025Updated last year
- A 20M RWKV v6 can do nonogram☆14Oct 18, 2024Updated last year
- ☆10Aug 18, 2023Updated 2 years ago
- The WorldRWKV project aims to implement training and inference across various modalities using the RWKV7 architecture. By leveraging diff…☆66Updated this week
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Aug 13, 2024Updated last year
- RWKV centralised docs for the community☆32Jan 17, 2026Updated 2 months ago
- RAG SYSTEM FOR RWKV☆53Dec 4, 2024Updated last year
- VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.☆244Jan 13, 2026Updated 2 months ago
- （WIP）long form speech generatoins☆31Apr 2, 2025Updated 11 months ago
- ☆11Oct 14, 2023Updated 2 years ago
- pure go for rwkv☆19Dec 31, 2023Updated 2 years ago
- Official implementation of the TTS model Lina-Speech☆179Jan 9, 2025Updated last year
- A large-scale RWKV v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy…☆48Oct 21, 2025Updated 5 months ago
- Mini Model Daemon☆12Nov 9, 2024Updated last year
- ☆178Jan 13, 2026Updated 2 months ago
- A highly customizable, full scale web backend for web-rwkv, built on axum with websocket protocol.☆28Apr 15, 2024Updated last year
- MiSS is a novel PEFT method that features a low-rank structure but introduces a new update mechanism distinct from LoRA, achieving an exc…☆32Mar 9, 2026Updated 2 weeks ago
- Course Project for COMP4471 on RWKV☆17Feb 11, 2024Updated 2 years ago
- RWKV-LM-V7(https://github.com/BlinkDL/RWKV-LM) Under Lightning Framework☆57Dec 24, 2025Updated 2 months ago
- A fast RWKV Tokenizer written in Rust☆54Aug 12, 2025Updated 7 months ago
- ☆23Oct 17, 2024Updated last year
- 实现Blip2RWKV+QFormer的多模态图文对话大模型，使用Two-Step Cognitive Psychology Prompt方法，仅3B参数的模型便能够出现类人因果思维链。对标MiniGPT-4，ImageBind等图文对话大语言模型，力求以更小的算力和资源实…☆42Jul 17, 2023Updated 2 years ago
- ESLTTS dataset☆16Feb 6, 2025Updated last year
- [EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner☆153Dec 14, 2025Updated 3 months ago
- Offline Speaker Diarization with SenseVoice by Sherpa ONNX.☆15Dec 23, 2024Updated last year
- Run ONNX RWKV-v4 models with GPU acceleration using DirectML [Windows], or just on CPU [Windows AND Linux]; Limited to 430M model at this…☆21Mar 16, 2023Updated 3 years ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆57Sep 1, 2025Updated 6 months ago
- ☆29Feb 4, 2025Updated last year
- Official Chinese documentation for RWKV | RWKV官方中文文档☆15Feb 20, 2026Updated last month
- BlackGoose Rimer: RWKV as a Superior Architecture for Large-Scale Time Series Modeling☆32Jul 11, 2025Updated 8 months ago
- Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications☆90Dec 20, 2024Updated last year
- continous batching and parallel acceleration for RWKV6☆22Jun 28, 2024Updated last year
- RWKV v5,v6 LoRA Trainer on Cuda and Rocm Platform. RWKV is a RNN with transformer-level LLM performance. It can be directly trained like …☆13Mar 24, 2024Updated last year
- Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK☆90Feb 14, 2026Updated last month
- ☆41Apr 30, 2025Updated 10 months ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆114Dec 2, 2025Updated 3 months ago
- This project is established for real-time training of the RWKV model.☆50May 17, 2024Updated last year
- 来自于文章Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition☆27Nov 20, 2024Updated last year
- RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's l…☆56Updated this week