Update app.py

app.py

@@ -17,54 +17,24 @@ pipe = pipeline(
     token=os.getenv('HF_TOKEN'),
 )
 
+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.")
 
-# Copied from https://github.com/openai/whisper/blob/c09a7ae299c4c34c5839a76380ae407e7d785914/whisper/utils.py#L50
-def format_timestamp(seconds: float, always_include_hours: bool = False, decimal_marker: str = "."):
-    if seconds is not None:
-        milliseconds = round(seconds * 1000.0)
-
-        hours = milliseconds // 3_600_000
-        milliseconds -= hours * 3_600_000
-
-        minutes = milliseconds // 60_000
-        milliseconds -= minutes * 60_000
-
-        seconds = milliseconds // 1_000
-        milliseconds -= seconds * 1_000
-
-        hours_marker = f"{hours:02d}:" if always_include_hours or hours > 0 else ""
-        return f"{hours_marker}{minutes:02d}:{seconds:02d}{decimal_marker}{milliseconds:03d}"
-    else:
-        # we have a malformed timestamp so just return it as is
-        return seconds
-
-
-def transcribe(file, task, return_timestamps):
-    outputs = pipe(file, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=return_timestamps)
-    text = outputs["text"]
-    if return_timestamps:
-        timestamps = outputs["chunks"]
-        timestamps = [
-            f"[{format_timestamp(chunk['timestamp'][0])} -> {format_timestamp(chunk['timestamp'][1])}] {chunk['text']}"
-            for chunk in timestamps
-        ]
-        text = "\n".join(str(feature) for feature in timestamps)
-    return text
-
+    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+    return  text
 
 demo = gr.Blocks()
-
-mic_transcribe = gr.Interface(
+ic_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
-        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
-        gr.inputs.Checkbox(default=False, label="Return timestamps"),
+        gr.Audio(sources="microphone", type="filepath"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
     outputs="text",
-    layout="horizontal",
+    # layout="horizontal",
     theme="huggingface",
-    title="Luganda Whisper Demo: Transcribe Audio",
+    title="Bambara Whisper Demo: 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"
@@ -76,22 +46,21 @@ mic_transcribe = gr.Interface(
 file_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
-        gr.inputs.Audio(source="upload", optional=True, label="Audio file", type="filepath"),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
-        gr.inputs.Checkbox(default=False, label="Return timestamps"),
+        gr.Audio(sources="upload", label="Audio file", type="filepath"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
     outputs="text",
-    layout="horizontal",
+    # layout="horizontal",
     theme="huggingface",
-    title="Luganda Whisper Demo: Transcribe Audio",
+    title="Bambara Whisper Demo: 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."
     ),
     examples=[
-        ["./ama_log-1514-E30_17.wav", "transcribe", False],
-        ["./ng_log-1614-E2_364.wav", "transcribe", True],
+        ["./ama_log-1514-E30_17.wav", "transcribe"],
+        ["./ng_log-1614-E2_364.wav", "transcribe"],
     ],
     cache_examples=True,
     allow_flagging="never",
@@ -100,4 +69,5 @@ file_transcribe = gr.Interface(
 with demo:
     gr.TabbedInterface([mic_transcribe, file_transcribe], ["Transcribe Microphone", "Transcribe Audio File"])
 
-demo.launch(enable_queue=True)
+demo.queue(max_size=10)
+demo.launch()