From e1441302504a001e16e4465e67221ebd9c43f0e4 Mon Sep 17 00:00:00 2001 From: boraytuna Date: Wed, 13 Nov 2024 09:42:00 -0500 Subject: [PATCH] Updated README to document personalized features --- README.md | 20 +++++++++++++++++++ .../transcription.txt | 1 + 2 files changed, 21 insertions(+) create mode 100644 Results/whisper-test1_20241113_093519/transcription.txt diff --git a/README.md b/README.md index 1a661d7..72d4695 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,23 @@ + +## Personalized Features + +This fork of OpenAI's Whisper includes the following enhancements: + +1. **Automated Folder Creation for Each Transcription Run**: + - Each time an audio file is transcribed, a unique folder is created under a parent folder named `Results`. + - This folder stores the transcription results, organized by audio file and timestamp. + - This makes it easy to review transcriptions from multiple audio files without overwriting previous results. + +2. **New Script: `run_and_save.py`**: + - This script allows you to transcribe an audio file and automatically save the output in a structured directory. + - Usage: + ```bash + python run_and_save.py /path/to/your_audio_file.mp3 --model tiny + ``` + - The output is saved in `Results/[audio_file_name]_[timestamp]/transcription.txt`. + - The `--model` argument lets you select the model size (options: `tiny`, `base`, `small`, `medium`, `large`). + + # Whisper [[Blog]](https://openai.com/blog/whisper) diff --git a/Results/whisper-test1_20241113_093519/transcription.txt b/Results/whisper-test1_20241113_093519/transcription.txt new file mode 100644 index 0000000..85a9031 --- /dev/null +++ b/Results/whisper-test1_20241113_093519/transcription.txt @@ -0,0 +1 @@ + Don't forget to subscribe. \ No newline at end of file