Spaces:
Running
Running
Bismay
commited on
Commit
·
5c39419
1
Parent(s):
86678b1
Add smolagents to requirements/ Update readme to reflect repo name
Browse files- README.md +10 -10
- requirements.txt +2 -1
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
emoji: 💬
|
4 |
colorFrom: green
|
5 |
colorTo: green
|
@@ -11,17 +11,17 @@ license: apache-2.0
|
|
11 |
short_description: Gradio MCP server to transcribe audio & video from URLs
|
12 |
---
|
13 |
|
14 |
-
#
|
15 |
|
16 |
## Overview
|
17 |
|
18 |
-
`
|
19 |
|
20 |
The repository contains the following main components:
|
21 |
- **`app.py`**: The main Gradio application file that runs the MCP server.
|
22 |
- **`transcription_tool.py`**: The core logic for handling file conversion and calling the transcription function.
|
23 |
- **`transcription.py`**: Contains the implementation for Whisper transcription using the `transformers` library.
|
24 |
-
- **`tool_config.json`**: Configuration details for the `
|
25 |
- **`requirements.txt`**: Lists the necessary Python dependencies.
|
26 |
- **`ffmpeg_setup.py`**: Script to ensure ffmpeg is available.
|
27 |
- **`logging_config.py`**: Configuration for logging.
|
@@ -32,8 +32,8 @@ The repository contains the following main components:
|
|
32 |
|
33 |
1. Clone this repository:
|
34 |
```bash
|
35 |
-
git clone https://huggingface.co/spaces/bismay/
|
36 |
-
cd
|
37 |
```
|
38 |
2. Install dependencies:
|
39 |
```bash
|
@@ -77,7 +77,7 @@ Example configuration for a client (like Cline) that supports SSE:
|
|
77 |
```json
|
78 |
{
|
79 |
"mcpServers": {
|
80 |
-
"
|
81 |
"url": "http://127.0.0.1:7860/gradio_api/mcp/sse"
|
82 |
}
|
83 |
}
|
@@ -90,15 +90,15 @@ Example configuration for a client (like Cline) that supports SSE:
|
|
90 |
|
91 |
This application is also hosted on Hugging Face Spaces, providing a publicly accessible MCP server. You can connect to this hosted server using the following URL:
|
92 |
|
93 |
-
`https://bismay-
|
94 |
|
95 |
To connect your MCP client (like Cline) to this hosted server, add a configuration entry similar to this:
|
96 |
|
97 |
```json
|
98 |
{
|
99 |
"mcpServers": {
|
100 |
-
"
|
101 |
-
"url": "https://bismay-
|
102 |
}
|
103 |
}
|
104 |
}
|
|
|
1 |
---
|
2 |
+
title: gradio-transcript-mcp - Gradio MCP Server for Transcription
|
3 |
emoji: 💬
|
4 |
colorFrom: green
|
5 |
colorTo: green
|
|
|
11 |
short_description: Gradio MCP server to transcribe audio & video from URLs
|
12 |
---
|
13 |
|
14 |
+
# gradio-transcript-mcp: A Gradio MCP Server for Audio/Video Transcription from URLs
|
15 |
|
16 |
## Overview
|
17 |
|
18 |
+
`gradio-transcript-mcp` is a Gradio application configured to function as an MCP (Model Control Protocol) server. It is designed to transcribe audio and video from URLs into text. Implementing OpenAI's Whisper and `ffmpeg` (via `yt-dlp`), this server enables MCP clients (like Cline) to process multimedia inputs efficiently by downloading and converting content from a given URL. It supports robust handling, including format conversion to WAV and dynamic device selection (CPU or GPU).
|
19 |
|
20 |
The repository contains the following main components:
|
21 |
- **`app.py`**: The main Gradio application file that runs the MCP server.
|
22 |
- **`transcription_tool.py`**: The core logic for handling file conversion and calling the transcription function.
|
23 |
- **`transcription.py`**: Contains the implementation for Whisper transcription using the `transformers` library.
|
24 |
+
- **`tool_config.json`**: Configuration details for the `gradio-transcript-mcp`.
|
25 |
- **`requirements.txt`**: Lists the necessary Python dependencies.
|
26 |
- **`ffmpeg_setup.py`**: Script to ensure ffmpeg is available.
|
27 |
- **`logging_config.py`**: Configuration for logging.
|
|
|
32 |
|
33 |
1. Clone this repository:
|
34 |
```bash
|
35 |
+
git clone https://huggingface.co/spaces/bismay/gradio-transcript-mcp
|
36 |
+
cd gradio-transcript-mcp
|
37 |
```
|
38 |
2. Install dependencies:
|
39 |
```bash
|
|
|
77 |
```json
|
78 |
{
|
79 |
"mcpServers": {
|
80 |
+
"gradio-transcript": {
|
81 |
"url": "http://127.0.0.1:7860/gradio_api/mcp/sse"
|
82 |
}
|
83 |
}
|
|
|
90 |
|
91 |
This application is also hosted on Hugging Face Spaces, providing a publicly accessible MCP server. You can connect to this hosted server using the following URL:
|
92 |
|
93 |
+
`https://bismay-gradio-transcript-mcp.hf.space/gradio_api/mcp/sse`
|
94 |
|
95 |
To connect your MCP client (like Cline) to this hosted server, add a configuration entry similar to this:
|
96 |
|
97 |
```json
|
98 |
{
|
99 |
"mcpServers": {
|
100 |
+
"gradio-transcript": {
|
101 |
+
"url": "https://bismay-gradio-transcript-mcp.hf.space/gradio_api/mcp/sse"
|
102 |
}
|
103 |
}
|
104 |
}
|
requirements.txt
CHANGED
@@ -7,4 +7,5 @@ yt-dlp==2025.1.15
|
|
7 |
transformers==4.48.1
|
8 |
torch==2.2.2
|
9 |
imageio-ffmpeg==0.6.0
|
10 |
-
numpy==1.24.3
|
|
|
|
7 |
transformers==4.48.1
|
8 |
torch==2.2.2
|
9 |
imageio-ffmpeg==0.6.0
|
10 |
+
numpy==1.24.3
|
11 |
+
smolagents==1.14.0
|