From 51d6ea8e18ed196ab2ea12339026cb85ec55559f Mon Sep 17 00:00:00 2001
From: Damien A <sepales.pret0h@icloud.com>
Date: Fri, 12 Jul 2024 12:15:17 +0200
Subject: [PATCH] Add `transcript-only` feature

---
 README.md      | 29 +++++++++++++++++++++--------
 src/summary.py | 15 ++++++++++++---
 2 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/README.md b/README.md
index d432b73..2acdf67 100644
--- a/README.md
+++ b/README.md
@@ -12,6 +12,7 @@ This tool is designed to provide a quick and concise summary of audio and video
 - **Local File Support**: Summarize audio files available on your local disk.
 - **Transcription**: Converts audio content to text using Whisper.
 - **Summarization**: Generates a concise summary using Mistral AI (Ollama).
+- **Transcript Only Option**: Option to only transcribe the audio content without generating a summary.
 
 ## Prerequisites
 
@@ -19,7 +20,7 @@ Before you start using this tool, you need to install the following dependencies
 
 - Python 3.8 or higher
 - `pytube` for downloading videos from YouTube.
-- `pathlib`for local file
+- `pathlib` for local file handling
 - `openai-whisper` for audio transcription.
 - [Ollama](https://ollama.com) for LLM model management.
 - `ffmpeg` (required for whisper)
@@ -36,17 +37,16 @@ cd audio-summary-with-local-LLM
 pip install -r src/requirements.txt
 ```
 
-### LLM Requierement
+### LLM Requirement
 
-[Download and install](https://ollama.com) Ollama to carry out LLM Management
-More details about LLM model supported can be discribe on the Ollama [github](https://github.com/ollama/ollama).
+[Download and install](https://ollama.com) Ollama to carry out LLM Management. More details about LLM models supported can be found on the Ollama [GitHub](https://github.com/ollama/ollama).
 
-Download and use Mistral model :
+Download and use the Mistral model:
 
 ```bash
 ollama pull mistral
 
-## Test the access :
+## Test the access:
 ollama run mistral "tell me a joke"
 ```
 
@@ -56,6 +56,7 @@ The tool can be executed with the following command line options:
 
 - `--from-youtube`: To download and summarize a video from YouTube.
 - `--from-local`: To load and summarize an audio or video file from the local disk.
+- `--transcript-only`: To only transcribe the audio content without generating a summary. This option must be used with either `--from-youtube` or `--from-local`.
 
 ### Examples
 
@@ -71,11 +72,23 @@ The tool can be executed with the following command line options:
    python src/summary.py --from-local <path-to-audio-file>
    ```
 
-The output summary will be saved in a markdown file in the specified output directory.
+3. **Transcribing a YouTube video without summarizing:**
+
+   ```bash
+   python src/summary.py --from-youtube <YouTube-Video-URL> --transcript-only
+   ```
+
+4. **Transcribing a local audio file without summarizing:**
+
+   ```bash
+   python src/summary.py --from-local <path-to-audio-file> --transcript-only
+   ```
+
+The output summary will be saved in a markdown file in the specified output directory, while the transcript will be saved in the temporary directory.
 
 ## Output
 
-The summarized content is saved as a markdown file named `summary.md` in the current working directory. This file includes the transcribed text and its corresponding summary.
+The summarized content is saved as a markdown file named `summary.md` in the current working directory. This file includes the transcribed text and its corresponding summary. If `--transcript-only` is used, only the transcription will be saved in the temporary directory.
 
 ## Sources
 
diff --git a/src/summary.py b/src/summary.py
index fb5c252..c2a90b6 100644
--- a/src/summary.py
+++ b/src/summary.py
@@ -3,10 +3,10 @@ import ollama
 import argparse
 from pytube import YouTube
 from pathlib import Path
-
+import os
 
 WHISPER_MODEL = "base"
-OLLAMA_MODEL = "mistral"
+OLLAMA_MODEL = "llama3"
 
 # Function to download a video from YouTube
 def download_from_youtube(url: str, path: str):
@@ -65,11 +65,16 @@ def main():
     group.add_argument("--from-youtube", type=str, help="YouTube URL to download.")
     group.add_argument("--from-local", type=str, help="Path to the local audio file.")
     parser.add_argument("--output", type=str, default="./summary.md", help="Output markdown file path.")
+    parser.add_argument("--transcript-only", action='store_true', help="Only transcribe the file, do not summarize.")
     
     args = parser.parse_args()
     
     # Set up data directory
     data_directory = Path("tmp")
+    # Check if the directory exists, if not, create it
+    if not data_directory.exists():
+        data_directory.mkdir(parents=True)
+        print(f"Created directory: {data_directory}")
   
     if args.from_youtube:
         # Download from YouTube
@@ -78,12 +83,16 @@ def main():
         file_path = data_directory / "to_transcribe.mp4"
     elif args.from_local:
         # Use local file
-        file_path = args.from_local
+        file_path = Path(args.from_local)
     
     print(f"Transcribing file: {file_path}")
     # Transcribe the audio file
     transcript = transcribe_file(str(file_path), data_directory / "transcript.txt")
     
+    if args.transcript_only:
+        print("Transcription complete. Skipping summary generation.")
+        return
+    
     print("Generating summary...")
     # Generate summary
     summary = summarize_text(transcript, "./")