Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -9,13 +9,15 @@ app_file: app.py
|
|
9 |
pinned: false
|
10 |
license: apache-2.0
|
11 |
short_description: smolagent tool to transcribe audio & video files
|
|
|
|
|
12 |
---
|
13 |
|
14 |
# TranscriptTool: A SmolAgent Tool for Audio/Video Transcription
|
15 |
|
16 |
## Overview
|
17 |
|
18 |
-
`TranscriptTool` is a
|
19 |
|
20 |
The repository contains three main components:
|
21 |
- **`transcription_tool.py`**: The core smolagent tool for transcription.
|
|
|
9 |
pinned: false
|
10 |
license: apache-2.0
|
11 |
short_description: smolagent tool to transcribe audio & video files
|
12 |
+
thumbnail: >-
|
13 |
+
https://cdn-uploads.huggingface.co/production/uploads/6339a72d593f7e383739348b/pE2FxleMKZLuJqjlg_ShH.png
|
14 |
---
|
15 |
|
16 |
# TranscriptTool: A SmolAgent Tool for Audio/Video Transcription
|
17 |
|
18 |
## Overview
|
19 |
|
20 |
+
`TranscriptTool` is a smolagent tool designed to transcribe audio and video files into text. Leveraging OpenAI's Whisper and `ffmpeg`, this tool empowers agents to process multimedia inputs efficiently. It supports robust file handling, including format conversion to WAV, dynamic device selection (CPU or GPU), and easy use within smolagents via the Hugging Face API.
|
21 |
|
22 |
The repository contains three main components:
|
23 |
- **`transcription_tool.py`**: The core smolagent tool for transcription.
|