Update app.py

app.py

@@ -1,10 +1,66 @@
 import os
 import openai
+import torch 
+
 import gradio as gr
+import pytube as pt
+from transformers import pipeline
+from huggingface_hub import model_info
 
 openai.api_key = os.getenv('OPEN_AI_KEY')
 hf_t_key = ('HF_TOKEN_KEY')
 
+MODEL_NAME = "openai/whisper-small" 
+lang = "en
+
+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.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
+
+def transcribe(microphone, file_upload):
+    warn_output = ""
+    if (microphone is not None) and (file_upload is not None):
+        warn_output = (
+            "WARNING: You've uploaded an audio file and or recorded . "
+            "The recorded file from the microphone uploaded, transcribed and immediately discarded.\n"
+        )
+
+    elif (microphone is None) and (file_upload is None):
+        return "ERROR: You have to either use the microphone or upload an audio file"
+
+    file = microphone if microphone is not None else file_upload
+
+    text = pipe(file)["text"]
+
+    return warn_output + text
+
+
+def _return_yt_html_embed(yt_url):
+    video_id = yt_url.split("?v=")[-1]
+    HTML_str = (
+        f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
+        " </center>"
+    )
+    return HTML_str
+
+
+def yt_transcribe(yt_url):
+    yt = pt.YouTube(yt_url)
+    html_embed_str = _return_yt_html_embed(yt_url)
+    stream = yt.streams.filter(only_audio=True)[0]
+    stream.download(filename="audio.mp3")
+
+    text = pipe("audio.mp3")["text"]
+
+    return html_embed_str, text
+
+
 def predict(message, history):
     history_openai_format = []
     for human, assistant in history:
@@ -57,5 +113,35 @@ A4 = gr.load(
               allow_flagging="never", 
               examples=["A gigantic celtic leprechaun wandering the streets of downtown Atlanta","A child eating pizza in a Brazilian favela"])
 
-pcp = gr.TabbedInterface([A1, A2, A3, A4], ["Chat", "Transcribe", "Describe", "Create"], theme= gr.themes.Glass(primary_hue="neutral", neutral_hue="slate"))
-pcp.queue().launch()
+mf_transcribe = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
+        gr.inputs.Audio(source="upload", type="filepath", optional=True),
+    ],
+    outputs="text",
+    layout="horizontal",
+    theme="huggingface",
+    title=" ",
+    description=(
+        "Transcribe recorded or audio files with the click of a button."
+    ),
+    allow_flagging="never",
+)
+
+yt_transcribe = gr.Interface(
+    fn=yt_transcribe,
+    inputs=[gr.inputs.Textbox(lines=1, placeholder="Paste your YouTube video URL here", label="YouTube Video URL")],
+    outputs=["html", "text"],
+    layout="horizontal",
+    theme="huggingface",
+    title=" ",
+    description=(
+        "Transcribe YouTube videos at the click of a button."
+      
+    ),
+    allow_flagging="never",
+)
+
+clp = gr.TabbedInterface([A1, mf_transcribe, yt_transcribe, A2, A3], ["Chat", "Transcribe Audio", "Transcribe YouTube Videos", "Describe", "Create"], theme= gr.themes.Glass(primary_hue="neutral", neutral_hue="slate"))
+clp.queue().launch()