el/youtubesummarizer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added some try except blocks and remove file after transcript is finished.

Browse Source
This commit is contained in:
Leonard Excoffier
2024-02-13 22:11:04 -05:00
parent 5d6d910439
commit a4e735563f
2 changed files with 35 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
audio.mp4
View File

Binary file not shown.

63
main.py
View File

@@ -1,6 +1,3 @@
# Youtube Video Summarizer
# Steps: Download audio of youtube video, transcribe text using openaimodels, from text use chatgpt models to summarize the content.
import os import os
from openai import OpenAI from openai import OpenAI
from pytube import YouTube from pytube import YouTube
@@ -17,38 +14,48 @@ def download_audio(video_url, output_filename='audio.mp4'):
return None return None
def transcription(OPENAI_API_KEY, audio_filename): def transcription(OPENAI_API_KEY, audio_filename):
client = OpenAI(api_key=OPENAI_API_KEY) try:
client = OpenAI(api_key=OPENAI_API_KEY)
audio_file = open(audio_filename, "rb") audio_file = open(audio_filename, "rb")
transcript = client.audio.transcriptions.create( transcript = client.audio.transcriptions.create(
file=audio_file, file=audio_file,
model="whisper-1", model="whisper-1",
language="en", language="en",
prompt="", prompt="",
response_format="json", response_format="json",
temperature=0.0 temperature=0.0
) )
print("Transcription finished") print("Transcription finished")
os.remove(audio_filename)
return transcript return transcript
except Exception as e:
print(f"Failed to transcript audio: {e}")
return None
def summarize(OPENAI_API_KEY, transcript): def summarize(OPENAI_API_KEY, transcript):
client = OpenAI(api_key=OPENAI_API_KEY) try:
stream = client.chat.completions.create( client = OpenAI(api_key=OPENAI_API_KEY)
model="gpt-4", stream = client.chat.completions.create(
messages=[ model="gpt-4",
{"role": "system", "content": "The prompt you will receive will be the transcript of a youtube video, your objective is to summarize the content of that transcript to the best of your ability, keep in mind there may be music or other parasit noises in the transcript."}, messages=[
{"role": "user", "content": str(transcript)} {"role": "system", "content": "The prompt you will receive will be the transcript of a youtube video, your objective is to summarize the content of that transcript to the best of your ability, keep in mind there may be music or other parasit noises in the transcript."},
], {"role": "user", "content": str(transcript)}
stream=True, ],
) stream=True,
)
for chunk in stream:
if chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="", flush=True)
except Exception as e:
print(f"Failed to summarize transcript: {e}")
return None
for chunk in stream:
if chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="", flush=True)
def main(): def main():
OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY') OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY')
video_url = str(input("video url:")) video_url = str(input("video url:"))