Add application file

.streamlit/secrets.toml

@@ -0,0 +1,12 @@
+open_ai = "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"
+serp = "bd4187d5f23e6a405a6470fe4fe03e61742cccf4"
+brwoserless = "0af8da42-e7eb-4c99-a98e-34d924416991"
+anthropic = "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"
+
+xi_api_key = "6d5e981fbb2643b06459981da55c4ae7"
+
+
+twilio_ssid = "AC892f3e7e653e2b4b8f5d03d916c036b5"
+twilio_auth = "6e8ca23b01873d18e1ba3c896fefa531"
+Twilio_from_number = "whatsapp:+14155238886"
+Zalpier_nla = "sk-ak-OVFYaWalqbjFPGFFnRcrvQf8Vu"

app.py

@@ -0,0 +1,126 @@
+import streamlit as st
+import whisper
+from pytube import YouTube
+from pydub import AudioSegment
+import pandas as pd
+import anthropic
+from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
+import io
+from elevenlabs import generate, set_api_key
+import subprocess
+from moviepy.video.io.ffmpeg_tools import ffmpeg_extract_subclip
+import os
+from elevenlabs import set_api_key
+
+set_api_key("6d5e981fbb2643b06459981da55c4ae7")
+
+
+def shorten_audio(filename):
+    cut_filename = "AutoDub/dub/cut_audio.mp4"
+    audio = AudioSegment.from_file(filename)
+    cut_audio = audio[:60 * 1000]
+    cut_audio.export(cut_filename, format="mp4")
+    return cut_filename
+
+
+def generate_translation(original_text, destination_language):
+    anthropic = Anthropic(
+        api_key="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")
+
+    prompt = (
+        f"{HUMAN_PROMPT} Please translate this video transcript into {destination_language}. You will get "
+        f"to the translation directly after I prompted 'the translation:'"
+        f"{AI_PROMPT} Understood, I will get to the translation without any opening lines."
+        f"{HUMAN_PROMPT} Great! this is the transcript: {original_text}; the translation:"
+    )
+
+    resp = anthropic.completions.create(
+        prompt=f"{prompt} {AI_PROMPT}",
+        model="claude-2.0",
+        stop_sequences=[HUMAN_PROMPT],
+        max_tokens_to_sample=900,
+    )
+
+    print(resp.completion)
+
+    return resp.completion
+
+
+def generate_dubs(text):
+    filename = "AutoDub/dub/output.mp3"
+
+    set_api_key(st.secrets['xi_api_key'])
+
+    audio = generate(
+        text=text,
+        voice="Sanchay",
+        model='eleven_multilingual_v1'
+    )
+
+    audio_io = io.BytesIO(audio)
+    insert_audio = AudioSegment.from_file(audio_io, format='mp3')
+    insert_audio.export(filename, format="mp3")
+
+    return filename
+
+
+def combine_video(video_filename, audio_filename):
+    ffmpeg_extract_subclip(video_filename, 0, 60, targetname="cut_video.mp4")
+
+    output_filename = "AutoDub/dub/output.mp4"
+
+    command = ["ffmpeg", "-y", "-i", "cut_video.mp4", "-i", audio_filename, "-c:v", "copy", "-c:a", "aac",
+               output_filename]
+
+    subprocess.run(command)
+
+    return output_filename
+
+
+st.title("AutoDubs 📺🎵")
+
+link = st.text_input("Link to Youtube Video", key="link")
+
+language = st.selectbox("Translate to", ("French", "German", "Hindi", "Italian", "Polish", "Portuguese", "Spanish"))
+
+if st.button("Transcribe!"):
+    print(f"downloading from link: {link}")
+
+    model = whisper.load_model("base")
+
+    yt = YouTube(link)
+
+    if yt is not None:
+        st.subheader(yt.title)
+        st.image(yt.thumbnail_url)
+        audio_name = st.caption("Downloading audio stream...")
+        audio_streams = yt.streams.filter(only_audio=True)
+        filename = audio_streams.first().download()
+        print("filename: ", filename)
+
+        if filename:
+            audio_name.caption(filename)
+            cut_filename = shorten_audio(filename)
+            transcription = model.transcribe(cut_filename)
+            print(transcription)
+
+            if transcription:
+                df = pd.DataFrame(transcription['segments'], columns=['start', 'end', 'text'])
+                st.dataframe(df)
+                print(transcription['text'])
+                dubbing_caption = st.caption("Dubbing...")
+                translation = generate_translation(transcription['text'], language)
+                dubbing_caption = st.caption("Begin dubbing...")
+                dubs_audio = generate_dubs(translation)
+                dubbing_caption.caption("Dubs generated! combining with the video...")
+
+                video_streams = yt.streams.filter(only_video=True)
+                video_filename = video_streams.first().download()
+
+                if video_filename:
+                    dubbing_caption.caption("Video downloaded! combining the video and the dubs...")
+                    output_filename = combine_video(video_filename, dubs_audio)
+
+                    if os.path.exists(output_filename):
+                        dubbing_caption.caption("Video successfully dubbed! Enjoy! 😀")
+                        st.video(output_filename)

requirements.txt

@@ -0,0 +1,94 @@
+altair==5.0.1
+anthropic==0.3.6
+anyio==3.7.1
+appnope==0.1.3
+asttokens==2.2.1
+attrs==23.1.0
+backcall==0.2.0
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.7.22
+charset-normalizer==3.2.0
+click==8.1.6
+decorator==4.4.2
+distro==1.8.0
+elevenlabs==0.2.21
+executing==1.2.0
+ffmpeg-python==0.2.0
+filelock==3.12.2
+future==0.18.3
+gitdb==4.0.10
+GitPython==3.1.32
+h11==0.14.0
+httpcore==0.17.3
+httpx==0.24.1
+idna==3.4
+imageio==2.31.1
+imageio-ffmpeg==0.4.8
+importlib-metadata==6.8.0
+ipython==8.14.0
+jedi==0.18.2
+Jinja2==3.1.2
+jsonschema==4.18.4
+jsonschema-specifications==2023.7.1
+llvmlite==0.40.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+more-itertools==10.0.0
+moviepy==1.0.3
+mpmath==1.3.0
+networkx==3.1
+numba==0.57.1
+numpy==1.24.4
+openai-whisper==20230314
+packaging==23.1
+pandas==2.0.3
+parso==0.8.3
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.5.0
+proglog==0.1.10
+prompt-toolkit==3.0.39
+protobuf==4.23.4
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==12.0.1
+pydantic==1.10.12
+pydeck==0.8.0
+pydub==0.25.1
+Pygments==2.15.1
+Pympler==1.0.1
+python-dateutil==2.8.2
+pytube==15.0.0
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+referencing==0.30.0
+regex==2023.6.3
+requests==2.31.0
+rich==13.4.2
+rpds-py==0.9.2
+six==1.16.0
+smmap==5.0.0
+sniffio==1.3.0
+stack-data==0.6.2
+streamlit==1.25.0
+sympy==1.12
+tenacity==8.2.2
+tiktoken==0.3.1
+tokenizers==0.13.3
+toml==0.10.2
+toolz==0.12.0
+torch==2.0.1
+tornado==6.3.2
+tqdm==4.65.0
+traitlets==5.9.0
+typing_extensions==4.7.1
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==2.0.4
+validators==0.20.0
+wcwidth==0.2.6
+whisper==1.1.10
+zipp==3.16.2