Delete README.md

README.md

@@ -1,202 +0,0 @@
----
-title: Video Editing
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
-license: mit
----
-
-
-# Welcome to Streamlit!
-
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
-
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
----
-title: Movie Dubber — Any Language to Hindi
-emoji: 🎬
-colorFrom: red
-colorTo: orange
-sdk: streamlit
-sdk_version: 1.32.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: Dub any video to Hindi — 100% free, open-source, CPU-only
----
-
-# 🎬 Movie Dubber — Any Language → Hindi
-
-Dub any video into Hindi automatically. Upload an MP4, get a Hindi dubbed video. 100% free, open-source, runs on CPU.
-
----
-
-## 🚀 Features
-
-| Feature | How it works |
-|---------|-------------|
-| 🎥 Upload video | MP4, AVI, MKV, MOV supported |
-| 🔊 Extract audio | ffmpeg pulls clean audio from video |
-| 📝 Transcribe speech | faster-whisper (CPU-optimised Whisper) with timestamps |
-| 🌏 Translate to Hindi | Helsinki-NLP MarianMT — free, no API key |
-| ✏️ Manual editing | Edit any translated line before generating speech |
-| 🗣️ Hindi TTS | gTTS — natural Hindi speech, instant generation |
-| 🎬 Merge video | ffmpeg merges Hindi audio with original BGM |
-| ⬇️ Download | Get final dubbed MP4 |
-
----
-
-## 📁 Project Structure
-
-```
-movie_dubber/
-├── app.py                  ← Main Streamlit app
-├── requirements.txt        ← Python dependencies
-├── README.md               ← This file
-└── utils/
-    ├── __init__.py
-    ├── audio_utils.py      ← Audio extraction & silence detection
-    ├── transcribe_utils.py ← Whisper transcription
-    ├── translate_utils.py  ← MarianMT translation
-    ├── tts_utils.py        ← Hindi TTS generation
-    └── video_utils.py      ← FFmpeg video merge
-```
-
----
-
-## 🤗 Deploy on Hugging Face Spaces (5 minutes)
-
-### Step 1 — Create a new Space
-
-1. Go to [huggingface.co/spaces](https://huggingface.co/spaces)
-2. Click **"Create new Space"**
-3. Fill in:
-   - **Space name:** `movie-dubber` (or any name)
-   - **SDK:** Streamlit
-   - **Hardware:** CPU Basic (free)
-4. Click **"Create Space"**
-
-### Step 2 — Upload files
-
-Option A — via the web UI:
-1. In your new Space, click **"Files"** tab
-2. Click **"Add file → Upload files"**
-3. Upload: `app.py`, `requirements.txt`, `README.md`
-4. Create a `utils/` folder and upload all 5 util files
-
-Option B — via Git:
-```bash
-git clone https://huggingface.co/spaces/YOUR_USERNAME/movie-dubber
-cd movie-dubber
-# copy all project files here
-git add .
-git commit -m "initial deploy"
-git push
-```
-
-### Step 3 — Wait for build
-
-Hugging Face will automatically:
-1. Install all `requirements.txt` packages
-2. Start your Streamlit app
-3. Show it live at `https://huggingface.co/spaces/YOUR_USERNAME/movie-dubber`
-
-> ⏱ First build takes ~3–5 minutes (downloading models)
-
----
-
-## 💻 Run Locally
-
-### Prerequisites
-- Python 3.9+
-- ffmpeg installed: `brew install ffmpeg` (Mac) or `sudo apt install ffmpeg` (Linux)
-
-### Setup
-
-```bash
-# 1. Clone / download the project
-git clone https://huggingface.co/spaces/YOUR_USERNAME/movie-dubber
-cd movie-dubber
-
-# 2. Create virtual environment
-python -m venv venv
-source venv/bin/activate   # Windows: venv\Scripts\activate
-
-# 3. Install dependencies
-pip install -r requirements.txt
-
-# 4. Run the app
-streamlit run app.py
-```
-
-Open your browser at `http://localhost:8501`
-
----
-
-## ⚙️ How Each Feature Works (Simple English)
-
-### 🔊 Audio Extraction
-We use **ffmpeg** to pull the audio out of your video file and save it as a WAV file at 16kHz. This format is what Whisper expects.
-
-### 📝 Transcription (Speech → Text)
-We use **faster-whisper** — a faster version of OpenAI's Whisper model. It listens to the audio and converts speech to text, along with start/end timestamps for each spoken phrase.
-- `tiny` model: fastest, good enough for clear speech
-- `base` model: best balance (recommended)
-- `small` model: most accurate, but 3–5 min per minute of audio on CPU
-
-### 🌏 Translation (Text → Hindi)
-We use **Helsinki-NLP MarianMT** models from Hugging Face. These are small neural machine translation models that run on CPU.
-- If your video is in a language with a direct → Hindi model, we use that
-- Otherwise we pivot: source language → English → Hindi (two steps)
-
-### ✏️ Manual Editing
-Before generating speech, you can edit any translated Hindi text directly in the app. This is important because machine translation isn't always perfect for movie dialogue.
-
-### 🗣️ Hindi TTS (Text → Speech)
-We use **gTTS** (Google Text-to-Speech) which is free and instant. It produces natural-sounding Hindi speech. Each segment is generated separately and placed at the correct timestamp.
-
-### 🎬 Video Merge
-We use **ffmpeg** to:
-1. Lower the original audio volume (keeps background music faintly audible)
-2. Mix the Hindi speech on top
-3. Combine with the original video stream (no re-encoding = fast!)
-
----
-
-## ⚠️ Limitations
-
-| Limitation | Why | Workaround |
-|------------|-----|------------|
-| Slow transcription on CPU | Whisper is GPU-optimised | Use `tiny` or `base` model, keep videos short |
-| No real speaker diarization | pyannote.audio needs GPU | Heuristic speaker switching is used |
-| No lip sync | Wav2Lip needs GPU | Speed-fitting keeps audio roughly in sync |
-| gTTS needs internet | It's an HTTP request | Works fine on HF Spaces |
-| File size limit | HF Spaces has RAM limits | Keep videos under 200MB |
-
----
-
-## 🛠️ Tech Stack
-
-| Component | Library | Why |
-|-----------|---------|-----|
-| Web UI | Streamlit | Easy, HF Spaces native |
-| Audio extraction | ffmpeg | Universal, fast |
-| Silence detection | pydub + librosa | Lightweight |
-| Transcription | faster-whisper | 4× faster than Whisper on CPU |
-| Translation | transformers (MarianMT) | Free, offline, good quality |
-| TTS | gTTS | Free, natural Hindi, instant |
-| Video merge | ffmpeg | Fast (copies video, no re-encode) |
-
----
-
-## 📄 License
-
-MIT — free to use, modify, and deploy.