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.
☆32Updated last week
Related projects ⓘ
Alternatives and complementary repositories for RWKV-ASR
- Official implementation of the TTS model Lina-Speech☆137Updated last week
- 单独维护的中文TTS☆35Updated 2 years ago
- Official Code for ParrotTTS☆42Updated last month
- Just another FastSpeech 2 but cleaner code :)☆25Updated 4 months ago
- ☆33Updated last year
- X-E-Speech: Joint Training Framework of Non-Autoregressive Cross-lingual Emotional Text-to-Speech and Voice Conversion☆70Updated 7 months ago
- Unofficial implementation of wavenext vocoder☆32Updated 2 months ago
- E2E TTS using Conditional Flow Matching (Experimental*)☆66Updated last year
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English☆74Updated this week
- Streaming Text to Speech Web UI☆13Updated 6 months ago
- Unofficial Pytorch implementation of SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speake…☆56Updated last year
- GPT-style network for phonemization with durations of text☆62Updated 8 months ago
- Chinese and English Bilinguish G2P☆20Updated last year
- 4G GPU & 10 Minutes for train☆12Updated last year
- ☆26Updated 8 months ago
- ☆39Updated last year
- Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark☆22Updated 4 months ago
- ☆34Updated 7 months ago
- All generative model in one for better TTS model☆66Updated 2 months ago
- SpeechDenoiser: Real-Time Speech Denoising with ONNX Welcome to SpeechDenoiser, a simple and effective solution for real-time speech den…☆44Updated 3 months ago
- VoiceBank-2023 is the speech corpus specially designed for constructing personalized Mandarin text-to-speech (TTS) systems.☆37Updated last year
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆53Updated 2 weeks ago
- noise reduction☆17Updated 4 months ago
- [WIP] Unofficial Implementation of Microsoft's PromptTTS2☆51Updated last year
- ☆13Updated 2 months ago
- My vocoder experiments☆21Updated last month
- Aligner for text-to-speech☆15Updated 4 months ago
- ☆16Updated 6 months ago
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆46Updated last year