more options

app.py

@@ -1,19 +1,62 @@
 from transformers import pipeline
 import gradio as gr
-from numpy import random 
-from PIL import Image
-pipe = pipeline(model="openai/whisper-medium")  # change to "your-username/the-name-you-picked"
+import numpy as np
+import pytube as pt
+
+model = pipeline(model="openai/whisper-medium")  # change to "your-username/the-name-you-picked"
+print(
+    f"Model is {'multilingual' if model.is_multilingual else 'English-only'} "
+    f"and has {sum(np.prod(p.shape) for p in model.parameters()):,} parameters."
+)
+
+options = dict(language='es', beam_size=5, best_of=5)
+transcribe_options = dict(task="transcribe", **options)
+translate_options = dict(task="translate", **options)
+
 
 def transcribe(audio):
-    text = pipe(audio)["text"]
-    return text
-
-iface = gr.Interface(
-    fn=transcribe, 
-    inputs=[gr.Audio(source="microphone", type="filepath"),], 
-    outputs="text",
-    title="Make transcription of audio",
+    transcription = model.transcribe(audio, **transcribe_options)
+    translation = model.transcribe(audio, **translate_options)
+    return transcription["text"], translation["text"]
+
+
+def youtube_transcribe(url):
+    yt = pt.YouTube(url)
+    stream = yt.streams.filter(only_audio=True).first()
+    audio = stream.download()
+    return transcribe(audio)
+
+
+mic_interface = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs=["text", "text"],
+    title="Transcribir y traducir audio",
+)
+
+audio_interface = gr.Interface(
+    fn=transcribe,
+    inputs="audio",
+    outputs=["text", "text"],
+    title="Transcribir y traducir audio",
 )
 
+video_interface = gr.Interface(
+    fn=transcribe,
+    inputs="video",
+    outputs=["text", "text"],
+    title="Transcribir y traducir audio",
+)
+
+youtube_interface = gr.Interface(
+    fn=youtube_transcribe,
+    inputs="text",
+    outputs=["text", "text"],
+    title="Transcribir y traducir video de YouTube",
+)
 
-iface.launch()
+if __name__ == "__main__":
+    gr.TabbedInterface(
+        [mic_interface, audio_interface, video_interface, youtube_interface],
+        ["Micrófono", "Audio", "Video", "YouTube"],
+    ).launch()

requirements.txt

@@ -2,4 +2,5 @@ transformers
 tensorflow
 torch
 sentencepiece
-numpy
+numpy
+pytube