{"id":29371716,"url":"https://github.com/jjaruna/autotranscriptgui","last_synced_at":"2026-05-20T14:35:40.590Z","repository":{"id":303024221,"uuid":"1014173732","full_name":"jjaruna/autoTranscriptGUI","owner":"jjaruna","description":"🎙️ Powerful GUI tool to transcribe and translate audio/video files using Whisper and OpenAI — fast, simple, and GPU-optimized.","archived":false,"fork":false,"pushed_at":"2025-07-05T08:15:30.000Z","size":0,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-05T08:34:16.549Z","etag":null,"topics":["fast-whisper","gui","openai-api","subtitulos","transcripcion","transcription","translate","whisper"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jjaruna.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-05T07:35:46.000Z","updated_at":"2025-07-05T08:17:29.000Z","dependencies_parsed_at":"2025-07-05T08:35:16.484Z","dependency_job_id":"06e00946-3f13-4a7d-9ce6-33e337b87b9d","html_url":"https://github.com/jjaruna/autoTranscriptGUI","commit_stats":null,"previous_names":["jjaruna/autotranscriptgui"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jjaruna/autoTranscriptGUI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjaruna%2FautoTranscriptGUI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjaruna%2FautoTranscriptGUI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjaruna%2FautoTranscriptGUI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjaruna%2FautoTranscriptGUI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jjaruna","download_url":"https://codeload.github.com/jjaruna/autoTranscriptGUI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jjaruna%2FautoTranscriptGUI/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264492282,"owners_count":23617025,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["fast-whisper","gui","openai-api","subtitulos","transcripcion","transcription","translate","whisper"],"created_at":"2025-07-09T16:01:01.951Z","updated_at":"2026-05-20T14:35:40.572Z","avatar_url":"https://github.com/jjaruna.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AutoTranscript GUI 🎙️\n\n**AutoTranscript** is a powerful, GPU-accelerated subtitle generator built on top of OpenAI's Whisper model. It features both a **command-line interface (CLI)** and a beautiful **CustomTkinter-based GUI** for users who prefer a graphical workflow.\n\nSupports:\n- Languages such as: English, Chinese, Japanese, Korean.\n- Local audio/video files.\n- Translate or transcribe YouTube videos using only the link.\n- Subtitle translation to English.\n- OpenAI API (for higher quality translations) NOT AVAILABLE \n\n---\n\n## ✨ Features\n\n- 🖥️ Full-featured **GUI with progress tracking**, real-time logs.\n- 📜 Generate `.srt` subtitle files from media files\n- 🌍 Supports multilingual transcription and optional **translation to English**\n- 🧠 Uses [Faster-Whisper](https://github.com/guillaumekln/faster-whisper) for fast GPU-accelerated transcription\n\n---\n## YOUTUBE TUTORIAL IN SPANISH\n\n(https://www.youtube.com/watch?v=dB6D1i1BjXc)\n\n---\n## 📸 GUI Preview\n\n\u003e ![image](https://github.com/user-attachments/assets/d328dff2-4d82-485c-95b8-162405a3e856)\n\n---\n\n## 🧩 Requirements\n\n- Python \n- NVIDIA GPU with CUDA (recommended)\n- Visual C++ Redistributable 14\n\n---\n## Installation for Releases \n\n - Extract the .rar file.\n - Go to the app folder.\n - At the top of the path bar, type cmd.\n - In the console, type: pip install -r requirements.txt.\n - Go back to the .bat file and run it.\n---\n\n## 📦 Installation\n\n```bash\ngit clone https://github.com/jjaruna/autoTranscriptGUI.git\ncd autoTranscriptGUI\npip install -r requirements.txt\n```\n---\n\n## 🚀 Launch the GUI\n\n```bash\npython AutoTranscriptGUI.py\n```\n### 🔍 Whisper Model Comparison Summary\n\n| Model               | VRAM (Min)    | ⚙️ Performance        | 🎯 Use Case                                               | 🌐 Translate into English |\n|--------------------|---------------|------------------------|-----------------------------------------------------------|--------------------------|\n| `tiny`             | ≥ 1 GB        | ⚡ Very Fast            | Quick tests, low-resource devices                         | ✅                        |\n| `base`             | ≥ 2 GB        | ⚡ Fast                 | Simple transcriptions, short audio                        | ✅                        |\n| `small`            | ≥ 4 GB        | ⚖️ Balanced            | Decent accuracy and speed for general use                | ✅                        |\n| `medium`           | ≥ 8 GB        | 🕒 Slower              | High-quality results for longer files                    | ✅                        |\n| `large-v1`         | ≥ 10 GB       | 🐢 Slower              | Older but still strong performer                         | ✅                        |\n| `large-v2`         | ≥ 10 GB       | 🐢 Slower              | More robust, especially with noisy inputs                | ✅                        |\n| `large-v3`         | ≥ 12 GB       | 🐌 Slowest             | Highest accuracy offline, latest version                 | ✅                        |\n| `large-v3-turbo`   | ≥ 8–10 GB     | ⚡ Fastest             | High-speed, high-accuracy, great multilingual support     | ❌                        |\n\n\n# 🧠 Recommendation\n\nAfter testing the `large-v3-turbo` model more than 10 times, I can confidently say it is the **fastest** and **most accurate** among all Whisper models included in this app.\n\n🖥️ My system has **4GB of VRAM**, and despite being under the recommended VRAM for large models, `large-v3-turbo` still performed exceptionally well.\n\n⚠️ **Note:** Your experience may vary depending on your GPU and available VRAM. Use this recommendation as a reference, **not a guarantee**. If you encounter performance issues, try smaller models like `medium` or `small`.\n\n---\n\n## 🖥️ CLI Mode (Optional)\n\nYou can still use the command-line version via `autosub.py`:\n\n```bash\npython autosub.py myvideo.mp4 -l ja --translate --model base\n```\n\n### CLI Options\n\n| Option              | Description |\n|---------------------|-------------|\n| `filename`          | File path |\n| `-l`, `--language`  | Force language (e.g. `en`, `es`, `zh`) |\n| `-t`, `--translate` | Translate to English |\n| `-o`, `--openai`    | Use OpenAI API |\n| `--model`           | Whisper model to use |\n| `--debug`           | Enable debug mode |\n| `--keep`            | Keep intermediate WAV file |\n\n---\n\n## 📝 Output\n\n- Subtitles are saved as `.srt` files in the same folder as your media.\n- If translated, original and translated text will be preserved.\n\n---\n\n## 🧪 Example GUI Workflow\n\n1. Open GUI\n2. Select video/audio file\n3. Choose language and Whisper model\n4. (Optional) Enable \"Translate to English\"\n5. Click **Start Transcription**\n\n---\n\n## 🙏 Credits\n\n- Built with [OpenAI Whisper](https://github.com/openai/whisper)\n- Powered by [Faster-Whisper](https://github.com/guillaumekln/faster-whisper)\n- GUI built with [CustomTkinter](https://github.com/TomSchimansky/CustomTkinter)\n- Thank you General Koi, for the great help in testing and reviewing the Japanese transcripts.\n\n---\n\n## 📄 License\n\nMIT License — free for personal and commercial use.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjjaruna%2Fautotranscriptgui","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjjaruna%2Fautotranscriptgui","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjjaruna%2Fautotranscriptgui/lists"}