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
Sorting:
- RWKV-SpeechChat is a real-time dialogue script based on a frozen 3B RWKV model with trained adapters and initial states. Various trained …☆28Jan 1, 2025Updated last year
- （WIP）long form speech generatoins☆31Apr 2, 2025Updated 11 months ago
- ☆11Oct 14, 2023Updated 2 years ago
- ☆23Oct 17, 2024Updated last year
- RAG SYSTEM FOR RWKV☆52Dec 4, 2024Updated last year
- ESLTTS dataset☆16Feb 6, 2025Updated last year
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Aug 13, 2024Updated last year
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆55Sep 1, 2025Updated 6 months ago
- RWKV centralised docs for the community☆31Jan 17, 2026Updated last month
- Syllable Segmentation and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model☆34Aug 27, 2023Updated 2 years ago
- 来自于文章Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition☆27Nov 20, 2024Updated last year
- Official implementation of the TTS model Lina-Speech☆178Jan 9, 2025Updated last year
- ☆10Aug 18, 2023Updated 2 years ago
- ☆11Nov 7, 2024Updated last year
- Phonemes and durations labeling based on whisper small☆11Jul 7, 2024Updated last year
- The WorldRWKV project aims to implement training and inference across various modalities using the RWKV7 architecture. By leveraging diff…☆65Dec 15, 2025Updated 2 months ago
- Onset-and-Offset-Aware Sound Event Detection☆21Feb 10, 2025Updated last year
- This is not remotely close to a finished product, and does not intend to nor does this claim to be working fine-tuning code for MaskGCT. …☆13Dec 4, 2024Updated last year
- A large-scale RWKV v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy…☆47Oct 21, 2025Updated 4 months ago
- Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications☆87Dec 20, 2024Updated last year
- ☆14Aug 1, 2025Updated 7 months ago
- Offline Speaker Diarization with SenseVoice by Sherpa ONNX.☆15Dec 23, 2024Updated last year
- unofficial pytorch implementation of HiFi-GAN with fast MISR.☆15Mar 21, 2023Updated 2 years ago
- A 20M RWKV v6 can do nonogram☆14Oct 18, 2024Updated last year
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆114Dec 2, 2025Updated 3 months ago
- VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.☆245Jan 13, 2026Updated last month
- CTC decoder with hotwords for ASR.☆34Apr 13, 2025Updated 10 months ago
- A highly customizable, full scale web backend for web-rwkv, built on axum with websocket protocol.☆28Apr 15, 2024Updated last year
- A simple command line tool to calculate WER for ASR.☆14Oct 14, 2024Updated last year
- A playground for experimenting with acoustic echo cancellation using a microphone, speaker, and ONNX.☆13Oct 22, 2024Updated last year
- A fast RWKV Tokenizer written in Rust☆54Aug 12, 2025Updated 6 months ago
- ☆175Jan 13, 2026Updated last month
- 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…☆41Jul 17, 2023Updated 2 years ago
- Streaming Vocos☆30Jun 10, 2025Updated 8 months ago
- ☆29Feb 4, 2025Updated last year
- Causal Speech Enhancement Based on a Two-Branch Nested U-Net Architecture Using Self-Supervised Speech Embeddings☆19Jun 6, 2025Updated 8 months ago
- A diffusion-based cross-lingual voice conversion model, as my bachelor's thesis☆44Jul 24, 2023Updated 2 years ago
- silero-vad pytorch implement☆35Nov 23, 2024Updated last year
- [ICASSP 2024] KNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels☆42Mar 20, 2024Updated last year