Update app.py

app.py

@@ -1,71 +1,22 @@
 import pathlib
-from faster_whisper import WhisperModel
 import yt_dlp
 import uuid
 import os
 import gradio as gr
 from tqdm import tqdm
 
-# List of all supported video sites here https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md
-def download_convert_video_to_audio(
-    yt_dlp,
-    video_url: str,
-    destination_path: pathlib.Path,
-) -> None:
-    ydl_opts = {
-        "format": "bestaudio/best",
-        "postprocessors": [
-            {  # Extract audio using ffmpeg
-                "key": "FFmpegExtractAudio",
-                "preferredcodec": "mp3",
-            }
-        ],
-        "outtmpl": f"{destination_path}.%(ext)s",
-    }
-    try:
-        print(f"Downloading video from {video_url}")
-        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-            ydl.download(video_url)
-        print(f"Downloaded video from {video_url} to {destination_path}")
-    except Exception as e:
-        raise (e)
 
-def segment_to_dict(segment):
-    segment = segment._asdict()
-    if segment["words"] is not None:
-        segment["words"] = [word._asdict() for word in segment["words"]]
-    return segment
-
-def download_video(video_url: str):
-    download_convert_video_to_audio(yt_dlp, video_url, f"{uuid.uuid4().hex}")
-
-def transcribe_video(video_url: str, word_timestamps: bool = True, model_size: str = "tiny"):
-    print(word_timestamps)
-    print("loading model")
-    model = WhisperModel(model_size, device="cpu", compute_type="int8")
-    # model = WhisperModel(model_size, device="cuda", compute_type="float16")
-    print("getting hex")
-    rand_id = uuid.uuid4().hex
-    print("doing download")
-    download_convert_video_to_audio(yt_dlp, video_url, f"{rand_id}")
-    segments, info = model.transcribe(f"{rand_id}.mp3", beam_size=5, word_timestamps=word_timestamps)
-    segments = [segment_to_dict(segment) for segment in segments]
-    total_duration = round(info.duration, 2)  # Same precision as the Whisper timestamps.
-    print(info)
-    os.remove(f"{rand_id}.mp3")
-    print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
-    print(segments)
+def transcribe_video(d_id_key: str, elv_key: str, full_text: str):
+    print("Test")
+    segments="Work In Progress"
+       
     return segments
 
-# print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
-
-# for segment in segments:
-#     print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
 
 demo = gr.Interface(fn=transcribe_video, inputs=[
-    gr.Textbox(label="Video URL"),
-    gr.Checkbox(label="Word Timestamps", info="Do you want word timestamps in the response?"),
-    gr.Dropdown(label="Model", value="tiny", choices=["tiny", "base", "small"])
+    gr.Textbox(label="D-Id API Key",placeholder="Paste your D-Id",type='password'),
+    gr.Textbox(label="Elevenlabs API Keys",placeholder="Paste Elevenlabs",type='password'),
+    gr.Textbox(lines=4, label=" Please input the text you wish to generate in order to make the photo speak.", placeholder="English Text here")
   ], outputs="text")
 
 demo.launch()