0.0.1

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
 title: Whisper Gradio Template
-emoji: 👀
+emoji: 🎙️
 colorFrom: indigo
 colorTo: green
 sdk: gradio
@@ -10,4 +10,17 @@ pinned: false
 short_description: hf space gradio app to transcribe audio using whisper ai
 ---
 
+# Whisper Gradio App
+
+This Gradio app uses OpenAI's Whisper model to transcribe audio files into multiple formats:
+- Plain text transcription
+- SRT subtitle format
+- Detailed JSON output with timestamps and metadata
+
+## Usage
+1. Upload an audio file (supports various formats)
+2. Wait for the model to process the audio
+3. Get the transcription in three different formats
+
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,96 @@
+import gradio as gr
+import whisper
+import torch
+import json
+import spaces
+from datetime import timedelta
+import os
+import zipfile
+from pathlib import Path
+
+def format_timestamp(seconds):
+    """Convert seconds to SRT timestamp format"""
+    td = timedelta(seconds=seconds)
+    hours = td.seconds//3600
+    minutes = (td.seconds//60)%60
+    seconds = td.seconds%60
+    milliseconds = td.microseconds//1000
+    return f"{hours:02d}:{minutes:02d}:{seconds:02d},{milliseconds:03d}"
+
+def save_files(text, srt, json_data, base_name):
+    """Save transcription in different formats and create zip"""
+    # Create output directory if it doesn't exist
+    output_dir = Path("transcriptions")
+    output_dir.mkdir(exist_ok=True)
+    
+    # Generate filenames
+    base_name = Path(base_name).stem
+    txt_path = output_dir / f"{base_name}.txt"
+    srt_path = output_dir / f"{base_name}.srt"
+    json_path = output_dir / f"{base_name}.json"
+    zip_path = output_dir / f"{base_name}_all.zip"
+    
+    # Save individual files
+    txt_path.write_text(text)
+    srt_path.write_text(srt)
+    json_path.write_text(json_data)
+    
+    # Create ZIP file
+    with zipfile.ZipFile(zip_path, 'w') as zipf:
+        zipf.write(txt_path, txt_path.name)
+        zipf.write(srt_path, srt_path.name)
+        zipf.write(json_path, json_path.name)
+    
+    return str(txt_path), str(srt_path), str(json_path), str(zip_path)
+
+@spaces.GPU
+def transcribe(audio_file):
+    # Load the Whisper model
+    model = whisper.load_model("large-v3-turbo")
+    
+    # Transcribe the audio
+    result = model.transcribe(audio_file)
+    
+    # Format as plain text
+    text_output = result["text"]
+    
+    # Format as JSON
+    json_output = json.dumps(result, indent=2)
+    
+    # Format as SRT
+    srt_output = ""
+    for i, segment in enumerate(result["segments"], 1):
+        start_time = format_timestamp(segment["start"])
+        end_time = format_timestamp(segment["end"])
+        text = segment["text"].strip()
+        srt_output += f"{i}\n{start_time} --> {end_time}\n{text}\n\n"
+    
+    # Save files and get paths
+    txt_file, srt_file, json_file, zip_file = save_files(
+        text_output, srt_output, json_output, 
+        os.path.basename(audio_file)
+    )
+    
+    return (
+        txt_file, srt_file, json_file, zip_file, text_output, srt_output, json_output
+    )
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(type="filepath", label="Upload Audio"),
+    outputs=[
+        gr.File(label="Download TXT"),
+        gr.File(label="Download SRT"),
+        gr.File(label="Download JSON"),
+        gr.File(label="Download All (ZIP)"),
+        gr.Textbox(label="Transcription", lines=5),
+        gr.Textbox(label="SRT Format"),
+        gr.JSON(label="JSON Output")
+    ],
+    title="Audio Transcription with Whisper",
+    description="Upload an audio file to transcribe it into text, SRT, and JSON formats using OpenAI's Whisper model. You can download the results in different formats or get everything in a ZIP file."
+)
+
+if __name__ == "__main__":
+    demo.launch()

example.py

@@ -0,0 +1,14 @@
+import gradio as gr
+import spaces
+import torch
+
+zero = torch.Tensor([0]).cuda()
+print(zero.device) # <-- 'cpu' 🤔
+
+@spaces.GPU
+def greet(n):
+    print(zero.device) # <-- 'cuda:0' 🤗
+    return f"Hello {zero + n} Tensor"
+
+demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
+demo.launch(share=True)

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+openai-whisper
+spaces
+torch