ahmetoner/whisper-asr-webservice

OpenAI Whisper ASR Webservice API

What it solves

It provides a ready-to-use REST API wrapper for OpenAI's Whisper models, allowing users to easily deploy and integrate speech-to-text capabilities into other applications without needing to build their own server infrastructure.

How it works

The project wraps several high-performance Whisper engines (OpenAI Whisper, Faster Whisper, and WhisperX) into a Dockerized web service. It uses FFmpeg to handle a wide variety of audio and video formats and provides a REST API with Swagger documentation for sending audio files and receiving transcriptions.

Who it’s for

Developers who need to deploy a self-hosted speech recognition service that supports multiple models and output formats (like SRT or VTT for subtitles) and can run on either CPU or GPU.

Highlights

  • Multiple Engine Support: Supports OpenAI Whisper, Faster Whisper, and WhisperX.
  • Flexible Output: Transcriptions can be exported as text, JSON, VTT, SRT, or TSV.
  • Advanced Transcription: Includes word-level timestamps, Voice Activity Detection (VAD) filtering, and speaker diarization via WhisperX.
  • Easy Deployment: Provided as Docker images for both CPU and GPU acceleration.
  • Broad Format Support: Integrated with FFmpeg for extensive audio/video compatibility.

Related

  • Project
    innovatorved/whisper.api

    A self-hosted, high-performance speech-to-text API powered by whisper.cpp that is Deepgram-compatible for easy integration.

  • Project
    jim60105/docker-whisperX

    A collection of optimized Docker images for WhisperX, providing pre-bundled ASR models for fast and efficient speech-to-text transcription with word-level timestamps.

  • Dispatch
    OpenAI Whisper Release

    OpenAI has released Whisper, an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data to improve robustness across accents, noise, and languages.

  • Project
    openai/whisper

    Whisper is OpenAI’s open‑source, transformer‑based speech‑to‑text system that handles transcription, language identification, and translation across many languages. It ships as a pip‑installable package with six model sizes (tiny → large, plus a fast “turbo” variant). The CLI (`whisper …`) and a simple Python API (`whisper.load_model(...).transcribe(...)`) let you turn audio files into text with just a few commands. The project runs on Python 3.8‑3.11, PyTorch, and requires ffmpeg (and optionally Rust for the tokenizer). All code and model weights are MIT‑licensed.

  • Project
    sandrohanea/whisper.net

    Dotnet bindings for OpenAI Whisper via whisper.cpp, enabling local speech-to-text and translation in .NET applications with extensive hardware acceleration support.