AGENDD / RWKV-SpeechChat
RWKV-SpeechChat is a real-time dialogue script based on a frozen 3B RWKV model with trained adapters and initial states. Various trained weights can be applied to perform a range of audio tasks, including automatic speech recognition (ASR), speech translation, speech question answering (QA), and more.
☆26Updated 2 months ago
Alternatives and similar repositories for RWKV-SpeechChat:
Users that are interested in RWKV-SpeechChat are comparing it to the libraries listed below
- This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the …☆48Updated 3 months ago
- Official implementation of the TTS model Lina-Speech☆157Updated 2 months ago
- a Frontier Japanese Speech Generation net☆28Updated 2 weeks ago
- This project is to train an RWKV LLM for TTS generation which compatible to other TTS engine(like fish/cosy/chattts).☆22Updated last week
- Open TTS models, built for streaming on the edge☆39Updated 2 weeks ago
- Audio tokenization, in the fastest way possible!☆49Updated 7 months ago
- (WIP)long form speech generatoins☆30Updated 3 months ago
- ☆39Updated last month
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆17Updated 4 months ago
- 4G GPU & 10 Minutes for train☆12Updated last year
- A collection of all our phonemeizers for dataset construction and inference☆22Updated last month
- ☆18Updated 10 months ago
- GPT-style network for phonemization with durations of text☆64Updated last year
- A low-bitrate single-codebook 16 kHz speech codec based on focal modulation☆81Updated last month
- Official repository of the IEEE SLT 2024 paper "Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT"☆37Updated this week
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆14Updated 9 months ago
- noise reduction☆17Updated 8 months ago
- StyleTTS 2 Optimized Training Fork☆26Updated last month
- ☆23Updated 2 months ago
- A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.☆37Updated 5 months ago
- DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors☆18Updated last month
- E2E TTS using Conditional Flow Matching (Experimental*)☆69Updated last year
- All generative model in one for better TTS model☆66Updated 6 months ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆64Updated 4 months ago
- ☆20Updated 5 months ago
- CTC decoder with hotwords for ASR.☆17Updated 2 months ago
- GPT for FACodec☆13Updated last year
- Pushing the Limits of Zero-shot End-to-End Speech Translation☆25Updated 3 months ago
- A collections of audio codecs with a standardized API☆11Updated last month
- My vocoder experiments☆27Updated 5 months ago