shashikg / WhisperS2T
An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine
β276Updated 3 weeks ago
Related projects: β
- π¬ ASR FastAPI server using faster-whisper and Multi-Scale Auto-Tuning Spectral Clustering for diarization.β188Updated last month
- Experimental code: sound file preprocessing to optimize Whisper transcriptions without hallucinated textsβ262Updated 7 months ago
- Minimal extension of OpenAI's Whisper adding speaker diarization with special tokensβ421Updated 10 months ago
- β241Updated 3 months ago
- Pybind11 bindings for Whisper.cppβ321Updated this week
- β431Updated 2 months ago
- The fastest Whisper optimization for automatic speech recognition as a command-line interface β‘οΈβ308Updated 3 months ago
- speechlib is a library that can do speaker diarization, transcription and speaker recognition on an audio file to create transcripts withβ¦β134Updated 3 weeks ago
- Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.β219Updated last year
- Improving transcription performance of OpenAI Whisper for CPU based deploymentβ234Updated last year
- β342Updated 6 months ago
- Speech recognition & diarisation solution with text alignment, deployed in AML pipelinesβ81Updated 4 months ago
- β384Updated this week
- Cog implementation of transcribing + diarization pipeline with Whisper & Pyannoteβ151Updated last week
- Whisper realtime streaming for long speech-to-text transcription and translationβ97Updated 7 months ago
- Joint speech-language model - respond directly to audio!β312Updated 2 months ago
- Whisper with Medusa headsβ774Updated last week
- β161Updated last month
- openvino version of openai/whisperβ157Updated 10 months ago
- A python package to build AI-powered real-time audio applicationsβ992Updated 2 months ago
- Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event β¦β312Updated 6 months ago
- An extremely fast implementation of whisper optimized for Apple Silicon using MLX.β519Updated 4 months ago
- Faster Tortoise inference then Tortoise Fast Forkβ122Updated 4 months ago
- β181Updated 3 months ago
- Efficient approach to speaker diarization using voice characteristics extractionβ56Updated 4 months ago
- Real-Time Whisper Voice Recognition with vosk model feedback.β103Updated last year
- β486Updated 4 months ago
- Python bindings for whisper.cppβ150Updated this week
- πΈπ¬ - a deep learning toolkit for Text-to-Speech, battle-tested in research and productionβ341Updated this week
- How to use OpenAIs Whisper to transcribe and diarize audio filesβ278Updated last year