pengzhendong / wetextLinks
Python runtime for WeTextProcessing (does not depend on Pynini)
☆11Updated 2 months ago
Alternatives and similar repositories for wetext
Users that are interested in wetext are comparing it to the libraries listed below
Sorting:
- ☆20Updated 7 months ago
- Torchaudio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆11Updated 5 months ago
- Unofficial implementation of ConvNeXt-TTS powered by lightning☆17Updated 7 months ago
- (WIP)long form speech generatoins☆31Updated 2 months ago
- ☆19Updated last year
- Offline Speaker Diarization with SenseVoice by Sherpa ONNX.☆12Updated 5 months ago
- An evaluation set for large-scale trained TTS models (Coming in Sep 2024)☆12Updated 9 months ago
- faster inference☆28Updated 4 months ago
- Streaming Text to Speech Web UI☆18Updated last year
- ☆28Updated 3 weeks ago
- noise reduction☆17Updated 11 months ago
- CTC decoder with hotwords for ASR.☆20Updated last month
- Just another FastSpeech 2 but cleaner code :)☆26Updated 11 months ago
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆27Updated 9 months ago
- Open Source Speech/Text Data on AI☆18Updated 2 years ago
- Self-supervised Generative LM-based Voice Conversion☆36Updated last month
- Tidy Tunes is an easy-to-use pipeline for mining high-quality audio data for speech generation models. To do so, it chains multiple open …☆16Updated last month
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆48Updated last year
- Try to replicate the architecture of MiniMaxTTS mentioned in it's technical report☆31Updated 3 weeks ago
- Megatts2 use HierSpeechpp's vocoder☆18Updated 6 months ago
- Streaming Vocos☆26Updated 4 months ago
- ☆26Updated 4 months ago
- A simple command line tool to calculate WER for ASR.☆14Updated 7 months ago
- A pitch detection model trained to be robust against noise and reverberation environments.☆25Updated 4 months ago
- G2pw's inference speed is accelerated by about 8-10 times. Change loop generated predictive data to only once and model loop prediction b…☆14Updated last year
- Text-To-Speech for NotebookLM☆29Updated 5 months ago
- Unofficial pytorch implementation of VISinger: Variational Inference with Adversarial Learning for End-to-end Singing Voice Synthesis (IC…☆15Updated 2 years ago
- PitchVC: Pitch Conditioned Any-to-Many Voice Conversion☆34Updated 11 months ago
- ICASSP2022 TTS&VC Summary☆14Updated 2 years ago
- Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks☆17Updated last year