Bismay commited on
Commit
5c39419
·
1 Parent(s): 86678b1

Add smolagents to requirements/ Update readme to reflect repo name

Browse files
Files changed (2) hide show
  1. README.md +10 -10
  2. requirements.txt +2 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- title: transcription-en-mcp - Gradio MCP Server for Transcription
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
- # TranscriptTool: A Gradio MCP Server for Audio/Video Transcription from URLs
15
 
16
  ## Overview
17
 
18
- `transcription-en-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 `transcription-en-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.
@@ -32,8 +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/transcription-en-mcp
36
- cd transcription-en-mcp
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
- "localTranscript": {
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-transcription-en-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
- "remoteTranscript": {
101
- "url": "https://bismay-transcription-en-mcp.hf.space/gradio_api/mcp/sse"
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