KoljaB / WhoSpeaksLinks
Efficient approach to speaker diarization using voice characteristics extraction
β101Updated 3 months ago
Alternatives and similar repositories for WhoSpeaks
Users that are interested in WhoSpeaks are comparing it to the libraries listed below
Sorting:
- Speech recognition & diarisation solution with text alignment, deployed in AML pipelinesβ97Updated last year
- π π€ Pip installable package for StyleTTS 2 human-level text-to-speech and voice cloningβ157Updated last year
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.β68Updated 3 weeks ago
- Fine Tune the Style-TTS2 Voice Modelβ253Updated 3 months ago
- Real-time processing and delivery of sentences from a continuous stream of characters or text chunks.β69Updated 2 months ago
- Real-time Voice Activity Detection (VAD) with some example use case like simple voice bot and live transcription (realtime transcription)β98Updated last month
- π Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. π§π₯π Advanced audio processing.β252Updated last year
- β170Updated 9 months ago
- speechlib is a library that can do speaker diarization, transcription and speaker recognition on an audio file to create transcripts withβ¦β237Updated last month
- β262Updated last year
- Open source inference code for Rev's modelβ429Updated 5 months ago
- β310Updated last year
- SoTA open-source TTSβ91Updated 3 months ago
- β100Updated last year
- A TTS model capable of generating ultra-realistic dialogue in one pass.β212Updated 5 months ago
- G2Pβ321Updated last month
- VoiceRestore: Flow-Matching Transformers for Universal Speech Restorationβ185Updated 5 months ago
- Collection of Open Source Speech Dataβ161Updated last week
- Speaker Diarization with Transformersβ69Updated 3 months ago
- Whisper realtime streaming for long speech-to-text transcription and translationβ121Updated last year
- β344Updated last year
- Create an LJSpeech structured voice dataset on wave inputβ35Updated last year
- Simulates talk with an AI that can express emotionsβ78Updated 3 months ago
- Experimental code: sound file preprocessing to optimize Whisper transcriptions without hallucinated textsβ342Updated 10 months ago
- An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engineβ473Updated last year
- A TTS model capable of generating ultra-realistic dialogue in one pass.β124Updated 2 months ago
- Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.β341Updated 2 years ago
- β378Updated last year
- Transcription and diarization (speaker identification)β33Updated 2 years ago
- Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detectionβ827Updated 4 months ago