pengzhendong / speaker-diarizationLinks
Offline Speaker Diarization with SenseVoice by Sherpa ONNX.
☆15Updated last year
Alternatives and similar repositories for speaker-diarization
Users that are interested in speaker-diarization are comparing it to the libraries listed below
Sorting:
- ☆23Updated last year
- faster inference☆28Updated last year
- （WIP）long form speech generatoins☆31Updated 9 months ago
- Streaming Text to Speech Web UI☆22Updated last year
- Just another FastSpeech 2 but cleaner code :)☆29Updated last year
- noise reduction☆17Updated last year
- ☆22Updated 5 months ago
- Official implementation of the paper titled "Age and Gender Recognition Using a Convolutional Neural Network with a Specially Designed Mu…☆27Updated last year
- Compute WER and SER for speech recognition evaluation☆23Updated last month
- An evaluation set for large-scale trained TTS models (Coming in Sep 2024)☆12Updated last year
- Streaming Vocos☆29Updated 7 months ago
- ☆25Updated 7 months ago
- CTC decoder with hotwords for ASR.☆34Updated 9 months ago
- E2E TTS using Conditional Flow Matching (Experimental*)☆71Updated 2 years ago
- ☆23Updated last year
- Data manipulation and transformation for audio signal processing, powered by PyTorch☆10Updated last year
- Official PyTorch inference code for the Interspeech 2025 paper: Efficient Speech Enhancement via Embeddings from Pre-trained Generative A…☆74Updated 7 months ago
- [ACMMM'2024] Generative Expressive Conversational Speech Synthesis☆43Updated last year
- Python runtime for WeTextProcessing (does not depend on Pynini)☆46Updated 2 months ago
- Try to replicate the architecture of MiniMaxTTS mentioned in it's technical report☆49Updated 4 months ago
- Official Code for ParrotTTS☆58Updated last year
- ☆36Updated 4 months ago
- silero-vad pytorch implement☆34Updated last year
- PitchVC: Pitch Conditioned Any-to-Many Voice Conversion☆36Updated last year
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆78Updated last year
- Inference code for Audiodec-Valle-Wenetspeech4TTS☆50Updated last year
- FlowMirror-HydraVox — A natively accelerated multi-head autoregressive TTS system derived from CosyVoice 3.0. It predicts multiple tokens…☆38Updated last week
- ☆29Updated 11 months ago
- Adaptive Vocoder for Custom Voice☆61Updated 3 years ago
- Megatts2 use HierSpeechpp's vocoder☆18Updated last year