First Commit

.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

@@ -1,5 +1,5 @@
 ---
-title: Whisper Audio Transcription
+title: Whisper Audio Transcription (zayuki)
 emoji: 🏢
 colorFrom: yellow
 colorTo: green

app.py

@@ -0,0 +1,12 @@
+import gradio as gr 
+from model import audio_transcribe
+
+iface = gr.Interface(
+    fn=audio_transcribe,
+    inputs=[gr.Audio(sources="upload", type="filepath", label="Upload Your Audio File")],
+    outputs=gr.Textbox(label="Audio Transcription"),
+    title="Audio Transcription - Whisper Large V3 Turbo",
+    description="Upload an audio file and get the transcribed text."
+)
+
+iface.launch(server_name="0.0.0.0", server_port=7860)

model.py

@@ -0,0 +1,16 @@
+from faster_whisper import WhisperModel
+
+model_size = "turbo"
+
+model = WhisperModel(model_size, device="cpu", compute_type="int8")
+
+def audio_transcribe(audio_path) -> str:
+    segments, info = model.transcribe(audio_path, beam_size=5)
+    full_transcript = " ".join([segment.text for segment in segments])
+    
+    return full_transcript
+
+if __name__ == "__main__":
+    audio_path = "T0055G0007S0001.wav"
+    transcript = audio_transcribe(audio_path)
+    print(transcript)