Update app.py

app.py

@@ -4,48 +4,42 @@ import spaces
 import torch
 
 from transformers import pipeline
-from transformers.pipelines.audio_utils import ffmpeg_read
 
-import tempfile
-import os
+# Pre-Initialize
+DEVICE = "auto"
+if DEVICE == "auto":
+    DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+print(f"[SYSTEM] | Using {DEVICE} type compute device.")
 
-MODEL_NAME = "openai/whisper-large-v3-turbo"
+# Variables
 BATCH_SIZE = 8
 
-device = 0 if torch.cuda.is_available() else "cpu"
-
-pipe = pipeline(task="automatic-speech-recognition", model=MODEL_NAME, chunk_length_s=30, device=device,)
-
+pipe = pipeline(task="automatic-speech-recognition", model="openai/whisper-large-v3-turbo", chunk_length_s=30, device=device)
 
 @spaces.GPU
 def transcribe(inputs, task):
-    if inputs is None:
-        raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
-
-    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
-    return  text
-
-
-demo = gr.Blocks(theme=gr.themes.Ocean())
-
-
-file_transcribe = gr.Interface(
-    fn=transcribe,
-    inputs=[
-        gr.Audio(sources="upload", type="filepath", label="Audio file"),
-        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
-    ],
-    outputs="text",
-    title="Whisper Large V3: Transcribe Audio",
-    description=(
-        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
-        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
-        " of arbitrary length."
-    ),
-    allow_flagging="never",
-)
-
-with demo:
-    gr.TabbedInterface([file_transcribe], ["Audio file"])
-
-demo.queue().launch(ssr_mode=False)
+    if inputs is None: raise gr.Error("Invalid input.")
+    output = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+    return output
+
+def cloud():
+    print("[CLOUD] | Space maintained.")
+
+# Initialize
+with gr.Blocks(css=css) as main:
+    with gr.Column():
+        gr.Markdown("🪄 Transcribe audio to text.")
+        
+    with gr.Column():
+        input = gr.Audio(sources="upload", type="filepath", label="Input"),
+        type = gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
+        submit = gr.Button("▶")
+        maintain = gr.Button("☁️")
+
+    with gr.Column():
+        output = gr.Textbox(lines=1, value=DEFAULT_INPUT, label="Output")
+            
+    submit.click(transcribe, inputs=[input, type], outputs=[output], queue=False)
+    maintain.click(cloud, inputs=[], outputs=[], queue=False)
+
+main.launch(show_api=True)