Lightweight, powerful real-time speech translation with multilingual support and a multilingual UI.
- asr-model
- translation
- audio-to-text
- crispasr
47,133 repositories indexed
25–38 of 38 · Most stars
Lightweight, powerful real-time speech translation with multilingual support and a multilingual UI.
TranslatedMeetDo — open-source Meeting-to-Action AI by 筑听 (Zhuting, "build listen") · JKinco Listen. Self-hosted live meetings, local ASR/LLM, structured minutes, DOCX/PDF.
LAS Recomp for Android: Link's Awakening (Switch) statically recompiled to native ARM64 for Android phones - touch controls, 60 fps frame generation, set up from your own game on the phone
Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian done right. 100% local, one native .exe, zero Python.
openvino version of openai/whisper
Github within the CLI :computer:
Generates Elm types, JSON decoders, JSON encoders and fuzz tests from JSON schema specifications
Push-to-talk voice dictation for Linux. 100% local, multilingual (25+ languages), with speaker diarization. Qt frontend, Rust backend on NVIDIA Parakeet via ONNX Runtime. KDE Plasmoid integrated.
Chrome extension for opening mastodon style links in your instance for ease of following
An example app that demos how to use TFLite to do automatic speech recognition on-device
OtosakuStreamingASR-iOS is a real-time speech recognition engine for iOS, built with Swift and Core ML. It uses a fast and lightweight streaming Conformer model optimized for on-device inference. Designed for developers who need efficient audio transcription on mobile.
Collection of ASR models for English TFLite models for faster inference.
A Clojure hierarchical set.
My Essential Tools: List of useful digital tools for everyday use