Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
Whisper
Whisper is an autoregressive language model developed by OpenAI. It is trained on a large corpus of text using a transformer architecture and is capable of generating high-quality natural language text. Whisper can be used for tasks such as language modeling, text completion, and text generation. It has shown impressive performance on various benchmarks and has been released by OpenAI to encourage research in the field of language modeling. Whisper is not yet available for public use, but it has the potential to transform the field of natural language processing and generate new opportunities for language-based applications.
- GitHub: https://github.com/topics/whisper
- Repo: https://github.com/openai/whisper
- Created by: OpenAI
- Released: August 2021
- Related Topics: machine-learning, artificial-intelligence, language-modeling,
- Last updated: 2025-01-24 00:34:40 UTC
- JSON Representation
https://github.com/ajxv/rtstt
Real time speech to text transcription using OpenAi whisper
live-transcription openai openai-whisper python3 transcription whisper
Last synced: 22 Dec 2024
https://github.com/electroneum/electroneum-web3.js
Electroneum SmartChain JavaScript API
api electroneum ethereum etn-sc javascript swarm typescript whisper
Last synced: 19 Jan 2025
https://github.com/rishabhmathur06/fine-tuning-whisper-small-for-asr-
This repository contains notebook that shows how to fine-tune OpenAI's Whisper model on custom Hindi dataset.
artificial-intelligence asr automatic-speech-recognition fine-tuning openai python whisper whisper-model
Last synced: 19 Dec 2024
https://github.com/akhkim/babel
Real-time Internal Audio Translate and Transcriber that uses Whisper model
ai internal-audio real-time transcription translation whisper
Last synced: 19 Dec 2024
https://github.com/bilelouahmed/vocal-assistant
Python voice assistant (based on SpeechRecognition, Whisper and XTTS models) designed to transcribe speech to text, translate across languages, engage in chat mode, and ultimately respond vocally.
chatbot llm mistral-7b neo4j python rag speech-recognition text-to-speech transcription whisper xtts
Last synced: 21 Dec 2024
https://github.com/huuquyet/phowhisper-tiny
Converted clone of PhoWhisper: Automatic Speech Recognition for Vietnamese (2024)
onnx-models phowhisper speech-recognition transformersjs vietnamese vinai whisper
Last synced: 06 Dec 2024
https://github.com/youknow2509/real-time-speech-to-text
Speech To Text in Real-Time
blackhole speech-recognition speech-to-text whisper whisper-api
Last synced: 19 Dec 2024
https://github.com/heyfoz/python-openai-whisper
This Python script provides a simple interface to transcribe audio files using the OpenAI API's speech-to-text functionality, powered by the Whisper model. The result is returned to the console as text or VTT (WebVTT) format.
ai api audio-transcription openai python speech-to-text whisper
Last synced: 19 Dec 2024
https://github.com/geo-y20/enhanced-learning-experience
IntelliLearn is a FastAPI-based application designed to process and transcribe audio and video files into text using the Whisper model. The application also supports processing PDF files to extract and summarize their content.
chat-application chatgpt educational-project fastapi groq-api huggingface lama llm pdf-files platform python speech-to-text text-summarization transformer whisper word2vec wordembedding
Last synced: 19 Dec 2024
https://github.com/samliebl/ai-whisper
Simple Node.js app: speech-to-text via whisper by OpenAI with file download.
nodejs openai speect-to-text transcription whisper whisper-ai
Last synced: 19 Dec 2024
https://github.com/nicknaskida/cog-whisper-diarization
Cog implementation of transcribing + diarization pipeline with Whisper & Pyannote
diarization openai-whisper pyannote replicate speaker-diarization whisper whisper-faster whisperx
Last synced: 20 Jan 2025
https://github.com/doctorpok42/pheere
Pheere is a simple virtual assistant
ai chatgpt elevenlabs ts virtual-assistant whisper
Last synced: 10 Jan 2025
https://github.com/sudiptab2100/waku-user-chat
Waku Chat using Usernames
communication-protocol decentralised-application decentralized ethereum ipfs libp2p waku waku-connect web3 whisper zk-snarks zkp
Last synced: 20 Dec 2024
https://github.com/obay-ismaeel/post-generator
An API that generates social media posts by implementing RAG with Llama-3
ai api fastapi llama llm python retrieval-augmented-generation social-media whisper
Last synced: 12 Oct 2024
https://github.com/aixerum/faster-whisper
faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU.
ctranslate2 gpu transcription whisper
Last synced: 07 Jan 2025
https://github.com/crucials/twaddle
speech analysis app that collects statistics like words frequencies and transcribed text
ai audio python python-eel speech-to-text vue whisper
Last synced: 24 Oct 2024
https://github.com/deepbiolab/customer-complaint-classification
An GenAI-powered pipeline leveraging Whisper, DALL-E, and GPT to transform customer complaints into actionable insights with automated transcription, visualization, and classification.
Last synced: 23 Jan 2025
https://github.com/fatma-moanes/voice-assistant
Voice Assistant for FM-Clinic: A multilingual AI-powered voice assistant for booking doctor appointments, leveraging advanced speech-to-text, text-to-speech, and large language models for seamless, natural user interactions.
ai-assistant arabic arabic-nlp aws-polly chatbot gpt groq langchain langsmith llm mongodb multilingual openai speech-recognition speech-to-text streamlit text-to-speech transcription voice-assistant whisper
Last synced: 26 Dec 2024
https://github.com/neiltron/autocap
ALL CAPS
closedcaptions ml subtitles transcription whisper
Last synced: 19 Dec 2024
https://github.com/yankeexe/tiktok-summarizer
Ask questions to a Tiktok video
ai function-calling llm llm-tool-call mini-app ollama pytorch seq2seq streamlit tiktok tool-calling transformers whisper
Last synced: 02 Jan 2025
https://github.com/evil0ctal/whisper-speech-to-text-api
An open source Speech-to-Text API. The project is based on OpenAI's Whisper model and uses the asynchronous features of FastAPI to efficiently wrap it and support more custom functions.
ai api fastapi openai-whisper speech-to-text speech-to-text-api whisper whisper-ai whisper-api
Last synced: 25 Oct 2024
https://github.com/nazago/meeting-minutes-generator
Script which takes a .wav audio file, performs speech-to-text using OpenAI/Whisper, and then, using Llama3, summarization and action point from the transcript generated
langchain-python llm-inference local-inference meeting-minutes ollama speech-to-text summarization whisper
Last synced: 02 Jan 2025
https://github.com/aitor-alvarez/whisper-lightning-finetuning
Whisper fine-tuning using Lightning
acoustic-features acoustic-model speech-recognition torch-lightning whisper
Last synced: 02 Jan 2025
https://github.com/asai95/speech-recognition-api
Simple but extensible API for Speech Recognition.
Last synced: 02 Jan 2025
https://github.com/nexuslux/simultaneous-interpretation
Simultaneous-Interpretation is an advanced tool for real-time simultaneous interpretation. It transcribes and translates spoken language from a microphone input instantaneously, continually refining translations for accuracy. Ideal for business meetings, educational settings, and live events, it enhances multilingual communication effortlessly.
agents asr faster-whisper openai pyaudio simultaneous-intepreting simultaneous-translation speech-recognition speech-to-text transcription translation whisper
Last synced: 09 Oct 2024
https://github.com/felipecastrosales/scripts
List of useful scripts.
audio helper-functions helpers ia pip python python3 script scripts video whisper whisper-ai
Last synced: 22 Dec 2024
https://github.com/sugarcane-mk/whisper
This repository provides a Python script for extracting speech embeddings using OpenAI's Whisper model. The embeddings are high-dimensional feature vectors that capture the acoustic properties of the input audio. These embeddings can be used for downstream tasks such as speech classification, clustering, and speaker recognition.
asr classification feature-extraction openai speech-processing speech-recognition speech-to-text svm-classifier whisper
Last synced: 02 Jan 2025
https://github.com/fkiller/whispertranscript
Transcribe voice from mic input using OpenAI Whisper API.
llm openai transcribe transcript transcription webaudio whisper
Last synced: 06 Jan 2025
https://github.com/yjg30737/pyqt-simple-whisper-gui
Whisper text-to-speech, speech-to-text example in PyQt5 GUI
openai pyqt pyqt-ai pyqt5 pyqt5-desktop-application pyqt5-examples pyqt5-gui whisper
Last synced: 03 Jan 2025
https://github.com/deshwalmahesh/whisper-fastapi-realtime
It is Front + Backend app that uses openai/whisper-large-v3-turbo in your consumer grade system to provide real live audio transcription
audio-transcription fastapi huggingface live pyaudio realtime transcription transformers whisper whisper-large
Last synced: 25 Oct 2024
https://github.com/bluebirdback/groq-subtitles
Batch video subtitle generation using Groq Whisper API
groq speech-to-text subtitles video whisper
Last synced: 21 Dec 2024
https://github.com/sbadulin/obsidian-dictation-plugin
Obsidian dictation plugin
dictation gpt-35-turbo obsidian obsidian-plugin openai speech-to-text whisper
Last synced: 07 Dec 2024
https://github.com/mrbuslov/reminder_4u_bot
AI Telegram Bot Reminder. You send a free-form text OR voice reminder, the AI bot records it and reminds you at the right time!
ai ai-bot aiogram chatgpt django gpt-3 gpt-4 gpt-models python reminder telegram-bot voice-recognition whisper
Last synced: 10 Jan 2025
https://github.com/patryk-ku/sasayaki
A small CLI tool that simplifies and automates the process of installing and using AI models to transcribe and translate videos.
automation cli faster-whisper gemini-api transcription translation whisper whisper-cpp
Last synced: 05 Jan 2025
https://github.com/julrog/jokes-on-you
Storyteller
ggj2024 global-game-jam openai unity whisper
Last synced: 17 Dec 2024
https://github.com/yousofss/speechtotext
Speech-to-Text using OpenAI's Whisper model
audio-to-text openai openai-whisper speech-to-text transcription whisper whisper-ai
Last synced: 09 Oct 2024
https://github.com/mai-reborn/mai-offline-transcriber
Offline audio/video transcriber using Whisper, saving to .txt or .srt. Ensures privacy, no external servers used.
asr audio-transcription offline-transcriber pyqt6 python speech-recognition video-transcription whisper
Last synced: 05 Jan 2025
https://github.com/educa-ch/educa24-speech-to-summary
Demonstrator for an open-source speech-to-summary workflow
langchain ollama open-source open-weight speech-to-text summarization whisper
Last synced: 11 Oct 2024
https://github.com/whisper-666/TikTok-Login
TikTok Login With No Captcha No Proxy (unlimited requests)
api combo combo-checker proxyless tiktok tiktok-api tiktok-followers tiktok-followers-generator tiktok-followers-software tiktok-login tiktok-views whisper
Last synced: 24 Oct 2024
https://github.com/man2dev/whisper-cpp
dev fork of https://src.fedoraproject.org/rpms/whisper-cpp
fedora fedora-repository linux whisper whisper-cpp whispercpp
Last synced: 09 Oct 2024
https://github.com/isladot/speech-to-text-whisper
A speech-to-text converter powered by OpenAI's Whisper model. Easy-to-use tool for transcribing audio into text with high accuracy.
ai python s2t speech-to-text whisper
Last synced: 19 Jan 2025
https://github.com/kolger/forty-two-transcribe
A Telegram bot that transcribes videos and audio messages to text via OpenAI Whisper API
openai self-hosted telegram whisper
Last synced: 25 Jan 2025
https://github.com/theaussiepom/wyoming-openai
OpenAI SST and TTS support for the Wyoming protocol
home-assistant home-assistant-assist openai sst tts whisper wyoming
Last synced: 21 Dec 2024
https://github.com/nanext21/vidcraft
VidCraft is an AI-driven backend application that generates videos from user-defined topics and backgrounds. It combines text, audio, and visuals using advanced AI services, making video creation accessible and efficient for developers and content creators alike.
elevenlabs fastapi ffmpgeg full-stack-web-development gemini-ai github-config image-generation machine-learning mern-project subtitles typescript video-generation whisper whisper-ai
Last synced: 19 Jan 2025
https://github.com/RingoMar/whisper-devcontainer
Openai whisper inside of vscode docker devcontainer using example files
ai devcontainer docker openapi python whisper
Last synced: 24 Oct 2024
https://github.com/arkapravo-ghosh/speech-to-text
Speech to Text Transcription using OpenAI Whisper v3 and FastAPI
ai fastapi huggingface machine-learning openai python3 speech-to-text transformers whisper
Last synced: 21 Dec 2024
https://github.com/datvm/openaiwhisperclient
A HTML page for using OpenAI Whisper API for transcripting, including making subtitles. JSON is also supported.
client-side openai subtitle timestamp transcript transcription whisper whisper-ai
Last synced: 15 Dec 2024
https://github.com/werserk/techstormhack-1st-place
Решение соревнования ТехШторм от корпорации ТатНефть по анализу активности членов команды на ВКС
pyannote speaker-diarization speech-recognition streamlit whisper
Last synced: 11 Jan 2025
https://github.com/baomeomeo/speech
A Speech-To-Text (with translation) library for Go; currently uses Whisper (runs locally if needed; no need in any API keys)
ai converter go golang library module package speech speech-recognition speech-to-text text whisper
Last synced: 13 Jan 2025
https://github.com/deshwalmahesh/interview-help-cheat-live
As the name suggests, it helps you cheat in your live interviews or video calls. It transcribes your audio and provides answers to your query in real time. Supports equation rendering, custom prompts, text selection and editing. It's basically chatGPT for cheating in interviews
audio-transcription chatgpt fastapi huggingface interview interviews live openai pyaudio realtime transcription transformers whisper whisper-large
Last synced: 31 Dec 2024
https://github.com/ts-azure-services/batch-transcription-examples
A repo to archive some code related to batch transcription for animation movies.
batch-transcription speech-to-text whisper
Last synced: 30 Nov 2024
https://github.com/notyusheng/transcribe-translate_kubernetes
Local web app for transcription and translation services for audio and video using Whisper models
docker full-stack k8s kubernetes nodejs react reactjs self-hosted speech-to-text transcribe translate whisper
Last synced: 23 Jan 2025
https://github.com/status-im/infra-role-status-go
Ansible role for status-go
ansible-role infra waku whisper
Last synced: 05 Jan 2025
https://github.com/MattCode64/Scriba
SCRIBA is a web application that transcribes audio files. It supports .mp3 files and provides the transcription results in a user-friendly interface.
fastapi python speech-to-text whisper
Last synced: 24 Oct 2024
https://github.com/sixiaolong1117/whisperpythonscript
一个简单的 Whisper Python 脚本,可以将媒体文件的音频通过 whisper 识别成文字,并通过 pysrt 保存为字幕。
pysrt python python3 whisper whisper-ai
Last synced: 16 Jan 2025
https://github.com/televisionninja/chat
Chat with an AI Vtuber
ai chatbot llama llm tts vtube-studio vtuber whisper
Last synced: 20 Nov 2024
https://github.com/studiowebux/tommygotchi
whisper, piper, llama-gpt, python, fun .. so much fun !
llama-gpt piper python3 whisper whisper-ai
Last synced: 05 Jan 2025
https://github.com/jplhughes/whisper_logit_lens
This Alignment Jam Hackathon project explores whether the concept of "logit lens" applies to the encoder and decoder layers in Whisper, an end-to-end speech recognition model.
alignment-jam asr interpretability interpretability-jam logitlens whisper
Last synced: 24 Oct 2024
https://github.com/miosipof/whisper_inference
OpenAI Whisper ASR inference on CPU with OpenVino, PyTorch or Huggingface
asr inference machine-learning openvino pytorch whisper
Last synced: 07 Jan 2025
https://github.com/jt-427/whisper-ui
A minimalist and elegant UI for OpenAI's Whisper speech-to-text model, built with React + Vite and Flask
flask openai react speech-to-text transcription vite whisper
Last synced: 19 Jan 2025
https://github.com/escarrie/transcriptaudio
This is a script that can be used to transcript audio file into text file using Whisper AI
Last synced: 17 Jan 2025
https://github.com/meain/raus
Record audio until silence (RAUS)
audio hammerspoon transcription whisper whisper-cpp
Last synced: 17 Jan 2025
https://github.com/yui-mhcp/speech_to_text
Speech-To-Text (STT) project
audio-transcription deepspeech jasper speech-to-text stt stt-api tensorflow2 video-transcription whisper
Last synced: 24 Oct 2024
https://github.com/mdbecker/whisper_cpp_macos_utils
Automated transcription workflow for macOS: Shell scripts to streamline audio recording, conversion, and transcription using whisper.cpp with macOS utilities like QuickTime Player and BlackHole-2ch.
audio-processing openai shell-scripts speech-to-text transcription whisper whisper-cpp
Last synced: 01 Dec 2024
https://github.com/madh93/whisper
🎙️ My Whisper stuff
docker openai speech-recognition speech-to-text whisper whisper-cpp
Last synced: 01 Dec 2024
https://github.com/tobybenjaminclark/intermew
👨💻 Realistic, generative simulated interviews for Durhack 2024. Built using Webscraping, OpenCV, Deepface, Whisper, OpenAI and Gamemaker.
computer-vision openai-api whisper
Last synced: 25 Jan 2025
https://github.com/teemow/mnote
Generates meeting notes and summaries from video recordings
ai chatgpt google-meet kubeai kubernetes meeting-minutes transcription video-transcription whisper
Last synced: 07 Dec 2024
https://github.com/armaggheddon/whisper2me
whisper2me is a telegram bot written with pyTelegramBotAPI that uses OpenAI's whisper to perform speech2text so you no longer have listen to voice messages 🤫🔇
docker openia pytelegrambotapi python whisper
Last synced: 25 Nov 2024
https://github.com/heng30/vtbox
It is an offline voice to text tool. Using whisper model to transcribe.
rust slint-ui voice2text whisper
Last synced: 21 Nov 2024
https://github.com/lukasbach/whisper-cpp-static
Static build of whisper.cpp by ggerganov
ai asr audio ml model recognition speech whisper
Last synced: 23 Jan 2025
https://github.com/EvilFreelancer/whisper-tests
Collection of experiments on OpenAI Whisper models
api-server docker-compose testing transcription whisper
Last synced: 24 Oct 2024
https://github.com/iamarunbrahma/smart-voice-assistant
A simple voice assistant to get your queries in speech format and generate answers using ChatGPT API in both text and audio format.
Last synced: 07 Dec 2024
https://github.com/charlot-dedjinou/hackathon-ia-multimodal-multilingue
Lors de ce hackathon, nous avons développé la solution Smart VT, une application web basée sur l'IA conçue pour sous-titrer et doubler n'importe quelle vidéo d'une langue à une autre (selon votre choix). Le projet s'appuie sur un frontend en React, des API Python pour le traitement des vidéos, et Node.js pour la gestion des sous-titres vidéo.
api dubble fastapi ffmpeg googletranslator mongodb moviepy nodejs openia reactjs subtitles whisper
Last synced: 12 Jan 2025
https://github.com/MattCode64/Scriba_Front
SCRIBA is a web application that transcribes audio files. It supports .mp3 files and provides the transcription results in a user-friendly interface.
speech-to-text vite vue vuejs whisper
Last synced: 24 Oct 2024
https://github.com/tristan-mcinnis/simultaneous-interpretation
Simultaneous-Interpretation is an advanced tool for real-time simultaneous interpretation. It transcribes and translates spoken language from a microphone input instantaneously, continually refining translations for accuracy. Ideal for business meetings, educational settings, and live events, it enhances multilingual communication effortlessly.
agents asr faster-whisper openai pyaudio simultaneous-intepreting simultaneous-translation speech-recognition speech-to-text transcription translation whisper
Last synced: 17 Jan 2025
https://github.com/miosipof/asr_train
Fine-tuning OpenAI Whisper for ASR tasks on low-size datasets
asr machine-learning nlp whisper
Last synced: 07 Jan 2025
https://github.com/levysantiago/upload-ai
Este é um sistema que utiliza Whisper e ChatGPT da OpenAI para gerar títulos e descrições a partir da análise de vídeos submetidos.
ai artificial-intelligence axios chatgpt fastify ffmpeg nlw-13 node openai prisma react rocketseat tailwindcss typescript vite whisper zod
Last synced: 12 Jan 2025
https://github.com/willdphan/little-jarvis-whisper
Jarvis, a GPT Voice Assistant made with speech recognition, OpenAI's Whisper, and Gradio
gradio openai voice-assistant voice-recognition whisper
Last synced: 24 Oct 2024
https://github.com/mariatepei/vt_thesis_mtepei
This repository accompanies my MSc Thesis for the degree Voice Technology, storing all referenced data and other relevant resources.
data-augmentation fastspeech2 speech-recognition whisper
Last synced: 09 Oct 2024
https://github.com/userpjm/whisper-youtube
Generate a SubRip subtitle file (srt) using Whisper for the audio of a YouTube video.
faster-whisper openai speech-to-text whisper
Last synced: 24 Oct 2024
https://github.com/firefly55lm/bisbigliatorev2
Automatic audio transcriber notebook based on Whisper
colab-notebook speech-to-text whisper
Last synced: 25 Nov 2024
https://gitlab.com/ifrz/asr-multi-lite
Testing of the main ASR frameworks with reduced models for low-resource languages speech recognition
Last synced: 24 Oct 2024
https://github.com/tylim88/Voicefu-back-end
Translate Speech Into Japanese
chatgpt speech-synthesis voicevox whisper
Last synced: 24 Oct 2024
https://github.com/luizcalaca/transcricao-medica
Full Stack + Whisper Transcription + Node.js REST API + VITE + React.js + Railway deploy
full-stack nodejs openai openai-api railway reactjs sequelize sequelize-orm vite whisper whisper-ai
Last synced: 25 Nov 2024
https://github.com/mickekring/top-of-mind-beromfabriken
Att ge beröm till en kollega kan kännas lite pinsamt, men forskning har visat att det kan få oss att må bättre på jobbet och att vi till och med blir mer produktiva. Att få höra att kollegor värdesätter och uppmärksammar en ökar ens välmående helt enkelt.
api gpt openai python transcription whisper
Last synced: 16 Jan 2025
https://github.com/ekito-station/whisper-api-unity
UnityでOpenAI Whisper APIを使って文字起こしを行ったサンプル
Last synced: 20 Dec 2024
https://github.com/rudrodip/kittyscribe
microservice for transcribing audio/video files to text and transcoding video
Last synced: 01 Dec 2024
https://github.com/ty-martz/audiologic
Python Module to process and predict on music attributes
machine-learning music python whisper
Last synced: 24 Oct 2024
https://github.com/huuquyet/phowhisper-small
Converted clone of PhoWhisper: Automatic Speech Recognition for Vietnamese (2024)
onnx-models phowhisper speech-recognition transformersjs vietnamese vinai whisper
Last synced: 06 Dec 2024
https://github.com/vlazic/json-verbose-to-vtt-converter
Transform `json_verbose` transcriptions from OpenAI, Groq, or command-line tools into VTT files with this Deno converter.
converter groq json json-verbose openai vtt webvtt whisper
Last synced: 26 Nov 2024