CiteIt.net

Building trust in media

How to Use Google Speech to Text to Generate a Transcript from a Youtube Video

by

Here’s how to generate transcripts with the Google Speech to Text api.

I’m providing instructions for running this on a micro Debian instance on Google Cloud Compute Engine.

Here’s how to download an interview Tyler Cowen did with Malcolm Gladwell.

1) Install YDL (The Youtube Download Library) for Commandline

The apt-get option seems to have an outdated version of ydl:  (I’m using Debian)

Alternate YDL Option:

If you can’t run youtube-dl because debian has on old version, try:

sudo apt install python3-pip
sudo pip3 install --upgrade youtube-dl

2) Get the FFMeg library

sudo apt-get update
sudo apt-get install ffmpeg

3) Running the YDL Download Command

youtube-dl --extract-audio --audio-format wav --audio-quality 5 --postprocessor-args "-ac 1" https://www.youtube.com/watch?v=ehlhrqSWPbo > malcolm_gladwell.wav

4) Copy .wav file to Storage Bucket

install gcsfuse to mount bucket

gcsfuse myBucket ~/path/to/mount
gsutil cp malcolm_gladwell.wav gs://bucket_name/

 

5) Upload filename.wav to Speech-text API

export GOOGLE_APPLICATION_CREDENTIALS=<i>~/.google-credentials.json</i>
gcloud ml speech recognize-long-running \
'gs://citeit_speech_text/malcolm-gladwell.wav' \
--include-word-time-offsets \
--language-code='en-US' \
--async
Check Job Progress
gcloud ml speech operations describe 2046110510732500677

Config Options

config = types.RecognitionConfig(
sample_rate_hertz=44100,
enable_word_time_offsets=True,
audio_channel_count=2,
language_code='en-US'

 

6) Download transcript.json

gcloud ml speech operations describe 2046110510732500677 > malcolm-gladwell-transcript.json

 

6a) Download Youtube Auto Generated transcript:

sudo pip3 install --upgrade webvtt-py

import webvtt

for caption in webvtt.read(downloads/5BXtgq0Nhsc.en.vtt'):
    print(caption.text)

 

7) Create timings.json

 

8) Create a Demo Page