0.0.1

Author: Noah-Jaffe

.gitignore

@@ -0,0 +1,7 @@
+.venv
+.vscode
+models
+*.mp4
+*.mkv
+*.mp3
+*.xlsx

README.md

@@ -0,0 +1,42 @@
+# Transcriber
+- Uses [`openai-whisper`](https://github.com/openai/whisper) to transcribe audio or video files.
+- Runs locally.
+- Outputs into a clean workbook by trascribed section and word. 
+- As always, TRUST NOTHING GENERATED BY AI, and always verify
+
+## Requirements:
+- Python3+
+- ffmpeg (included in repo)
+- beefy pc(?)
+- internet (for model download, on the first time you use it)
+---
+# How to use:
+0. install requirements
+    - `pip install -r requirements.txt`
+1. Start application.
+    - `python ./transcribe.py`
+2. Select files (button) to be transcribed.
+3. Select AI model to use from the drop down.
+    - Hover over the drop down to see some selection guidance. Choose one that your device can handle.
+    - [Read more about the models here.](https://github.com/openai/whisper?tab=readme-ov-file#available-models-and-languages)
+4. Start transcript (button).
+5. Wait for final results popup to appear.
+6. Review resulting transcripts.
+---
+#### What the running program looks like.
+![What the running program looks like.](docs\readme_demo.png)
+#### Completion notification.
+![Completion notification.](docs\readme_transcripts_complete.png)
+#### Output files can be found next to the input files.
+![Output files can be found next to the input files.](docs\readme_output_location.png)
+#### Output contents is 2 sheets, one by segment and one by word.
+![Output contents is 2 sheets, one by segment and one by word.](docs\readme_demo_outputs.png)
+##### Don't blame me if the AI is bad. (Same input as previous pic, but got different output.)
+![Same input but different output](docs\readme_same_input_different_output.png)
+
+---
+### Backlog ideas:
+- [ ] Additional AI sources?
+- [ ] Advanced/Runtime configuration of AI parameters?
+- [ ] Bundle into single executable to be more user friendly?
+- [ ] Select subframe of time to transcribe from?

docs/readme_demo.png

@@ -0,0 +1,28 @@
+# used:
+ffmpeg-python==0.2.0
+openai-whisper==20240930
+XlsxWriter==3.2.2
+# deps:
+certifi==2025.1.31
+charset-normalizer==3.4.1
+colorama==0.4.6
+filelock==3.17.0
+fsspec==2025.2.0
+future==1.0.0
+idna==3.10
+jinja2==3.1.5
+llvmlite==0.43.0
+MarkupSafe==3.0.2
+more-itertools==10.6.0
+mpmath==1.3.0
+networkx==3.2.1
+numba==0.60.0
+numpy==2.0.2
+regex==2024.11.6
+requests==2.32.3
+sympy==1.13.1
+tiktoken==0.9.0
+torch==2.6.0
+tqdm==4.67.1
+typing-extensions==4.12.2
+urllib3==2.3.0