Update README.md

README.md

@@ -12,3 +12,54 @@ short_description: filler
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# 🎙️ CrisperWhisper Speech-to-Text
+
+This Hugging Face Space provides a speech-to-text transcription service powered by the [nyrahealth/CrisperWhisper](https://huggingface.co/nyrahealth/CrisperWhisper) model. Upload audio files and get transcribed text with word-level timestamps.
+
+## Features
+
+- Transcribe audio files to text with word-level timestamps
+- Support for multiple audio formats (MP3, WAV, M4A, OGG, FLAC)
+- Up to 30MB file size support
+- Simple web interface using Gradio
+- REST API endpoint for programmatic access
+
+## How to Use
+
+1. Upload an audio file using the interface
+2. Click "Transcribe"
+3. View both the plain text transcription and detailed JSON output with timestamps
+
+## API Usage
+
+You can also use this Space programmatically via the REST API:
+
+```python
+import requests
+
+url = "https://your-space-name.hf.space/api/predict"
+files = {'audio_input': open('/path/to/your-audio-file.mp3', 'rb')}
+
+response = requests.post(url, files=files)
+print(response.json())
+```
+
+## Model Details
+
+This app uses the [nyrahealth/CrisperWhisper](https://huggingface.co/nyrahealth/CrisperWhisper) model, which is optimized for high-quality speech transcription with timestamp information.
+
+## System Requirements
+
+For optimal performance, this Space should be run with:
+- GPU acceleration
+- At least 8GB RAM
+
+---
+
+tags:
+- speech-to-text
+- transcription
+- whisper
+- gradio
+- audio-processing