Anoncheg1 / stable-ts-con
Stable timestamps and confidence score for words of OpenAI's Whisper outputs down to word-level.
☆25Updated last year
Related projects ⓘ
Alternatives and complementary repositories for stable-ts-con
- Zero-shot multimodal punctuation insertion and truecasing using Whisper☆99Updated last year
- Speaker change detection using SincNet and an LSTM/Transformer☆44Updated 4 months ago
- ☆66Updated last year
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆71Updated last year
- Reproducible experimental protocols for multimedia (audio, video, text) database☆84Updated last month
- This is the M-AILABS Speech Dataset☆22Updated 4 months ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated 9 months ago
- Promting Whisper for Audio-Visual Speech Recognition, Code-Switched Speech Recognition, and Zero-Shot Speech Translation☆134Updated 10 months ago
- ☆32Updated 2 months ago
- Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning (ASRU2023)☆26Updated last year
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆83Updated last month
- Unofficial implementation of miipher☆112Updated 7 months ago
- Online streaming speaker change detection model in Pytorch☆36Updated last year
- ☆16Updated 3 years ago
- Various speech datasets made available to the public☆99Updated last month
- ☆17Updated last year
- VoicePAT is a modular and efficient toolkit for voice privacy research, with main focus on speaker anonymization.☆46Updated 6 months ago
- Clustering-based methods for overlapping diarization☆70Updated 10 months ago
- Prosodic Speech Segmentation with Transformers☆23Updated 8 months ago
- Speaker identification/verification models for Machine Learning for Computer Vision class at UNIBO☆58Updated 2 years ago
- NPTEL2020: Speech2Text dataset for Indian-English Accent☆72Updated 2 years ago
- The implementation for "Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System".☆18Updated 2 months ago
- A data annotation pipeline to generate high-quality, large-scale speech datasets with machine pre-labeling and fully manual auditing.☆100Updated last year
- Putting flows on top of neural transducers for better TTS☆63Updated 3 weeks ago
- ☆37Updated 3 years ago
- Finetuning VITS Efficiently☆32Updated last year
- A mini, simple, and fast end-to-end automatic speech recognition toolkit.☆47Updated last year
- MeetEval - A meeting transcription evaluation toolkit☆78Updated 3 weeks ago
- A python library for voice activity detection (VAD) for speech/non-speech segmentation.☆83Updated 2 years ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 4 years ago