From 4ed0bcb786d53b403013c6bc6ea4af76b3587806 Mon Sep 17 00:00:00 2001 From: Kayn Ty Date: Sat, 27 Mar 2021 14:38:39 +0100 Subject: [PATCH] up scripts --- conversion_simple_fr.py | 2 +- log_ydl.txt | 7 ------- website/log_ydl.txt | 8 ++++++++ website/youtube-dl.sh | 34 ++++++++++++++++++++++++---------- 4 files changed, 33 insertions(+), 18 deletions(-) delete mode 100644 log_ydl.txt diff --git a/conversion_simple_fr.py b/conversion_simple_fr.py index c248ff3..69c3126 100644 --- a/conversion_simple_fr.py +++ b/conversion_simple_fr.py @@ -1,4 +1,4 @@ -#!/usr/bin/env python3 +#!/usr/bin/python3 from vosk import Model, KaldiRecognizer, SetLogLevel import sys diff --git a/log_ydl.txt b/log_ydl.txt deleted file mode 100644 index e16f0b5..0000000 --- a/log_ydl.txt +++ /dev/null @@ -1,7 +0,0 @@ -total 0 --rw-rw-r-- 1 tykayn tykayn 0 mars 27 10:27 0_output_.json --rw-rw-r-- 1 tykayn tykayn 0 mars 27 10:27 1_converted_.txt --rw-rw-r-- 1 tykayn tykayn 0 mars 27 10:27 2_without_nulls_.txt --rw-rw-r-- 1 tykayn tykayn 0 mars 27 10:27 3_without_nulls_.txt --rw-rw-r-- 1 tykayn tykayn 0 mars 27 10:27 4_phrases_.txt - sam. 27 mars 2021 10:27:22 CET ###### end conversion __ essai __ https://peertube.cipherbliss.com/videos/watch/e6a37508-042e-4d83-8598-5d36b764bb3d diff --git a/website/log_ydl.txt b/website/log_ydl.txt index 2448350..238a53c 100644 --- a/website/log_ydl.txt +++ b/website/log_ydl.txt @@ -1,2 +1,10 @@ sam. 27 mars 2021 10:27:21 CET ###### start conversion __ essai __ https://peertube.cipherbliss.com/videos/watch/e6a37508-042e-4d83-8598-5d36b764bb3d sam. 27 mars 2021 10:30:16 CET ###### start conversion __ essai __ https://peertube.cipherbliss.com/videos/watch/e6a37508-042e-4d83-8598-5d36b764bb3d + Sat Mar 27 13:50:27 CET 2021 ###### start conversion __ essai.wav __ https://peertube.cipherbliss.com/videos/watch/e6a37508-042e-4d83-8598-5d36b764bb3d + Sat Mar 27 14:00:20 CET 2021 ###### start conversion __ essai.wav __ https://peertube.cipherbliss.com/videos/watch/e6a37508-042e-4d83-8598-5d36b764bb3d + Sat Mar 27 14:02:25 CET 2021 ###### start conversion __ essai __ https://peertube.cipherbliss.com/videos/watch/e6a37508-042e-4d83-8598-5d36b764bb3d + Sat Mar 27 14:03:13 CET 2021 ###### start conversion __ essai __ https://peertube.cipherbliss.com/videos/watch/e6a37508-042e-4d83-8598-5d36b764bb3d + Sat Mar 27 14:03:52 CET 2021 ###### start conversion __ essai __ https://peertube.cipherbliss.com/videos/watch/e6a37508-042e-4d83-8598-5d36b764bb3d + Sat Mar 27 14:23:15 CET 2021 ###### start conversion __ batman_script __ https://peertube.cipherbliss.com/videos/watch/193545b2-3cd5-468a-b563-e17d0121e1bf + Sat Mar 27 14:23:18 CET 2021 ###### end conversion __ batman_script __ https://peertube.cipherbliss.com/videos/watch/193545b2-3cd5-468a-b563-e17d0121e1bf + Sat Mar 27 14:24:10 CET 2021 ###### start conversion __ batman_script __ https://peertube.cipherbliss.com/videos/watch/193545b2-3cd5-468a-b563-e17d0121e1bf diff --git a/website/youtube-dl.sh b/website/youtube-dl.sh index 3d7b446..13b1e9d 100755 --- a/website/youtube-dl.sh +++ b/website/youtube-dl.sh @@ -3,24 +3,38 @@ touch log_ydl.txt echo " $(date) ###### start conversion __ $1 __ $2" >> log_ydl.txt UNIQID=$1 -mkdir -p ../input/ydl -rm -rf ../input/ydl/$UNIQID.mp3 -rm -rf ../input/ydl/$UNIQID +# mkdir -p ../input/ydl +# rm -rf ../input/ydl/$UNIQID.mp3 +# rm -rf ../input/ydl/$UNIQID URL=$2 OUTPUT="../input/ydl/$UNIQID/base.mp3" + +echo " \n output : \n" +echo $OUTPUT + mkdir ../input/ydl/$UNIQID -youtube-dl --extract-audio --audio-format mp3 --audio-quality 0 --output $OUTPUT $URL +youtube-dl --extract-audio --audio-format mp3 --audio-quality 0 --output $OUTPUT $URL --no-continue + +ls -larth ../input/ydl/$UNIQID ffmpeg -i "../input/ydl/$UNIQID/base.mp3" -ac 1 "../input/ydl/$UNIQID/mono_canal.wav" -cd .. OUT_DIR="input/ydl/$UNIQID" -python3 ./conversion_simple_fr.py $OUT_DIR/mono_canal.wav > $OUT_DIR/0_output_$FILE_NAME.json -jq .text $OUT_DIR/0_output_$FILE_NAME.json > $OUT_DIR/1_converted_$FILE_NAME.txt - sed 's/null//g' $OUT_DIR/1_converted_$FILE_NAME.txt > $OUT_DIR/2_without_nulls_$FILE_NAME.txt - sed 's/^ *//; s/ *$//; /^$/d' $OUT_DIR/2_without_nulls_$FILE_NAME.txt > $OUT_DIR/3_without_nulls_$FILE_NAME.txt - sed 's/\"//g' $OUT_DIR/3_without_nulls_$FILE_NAME.txt > $OUT_DIR/4_phrases_$FILE_NAME.txt +mkdir $OUT_DIR + +echo " $(date) ###### lancer la transcription" +pwd +ls -larth input/ydl/$UNIQID/ +echo "\n" + +cd .. +bash transcript.sh input/ydl/$UNIQID/mono_canal.wav + +#jq .text $OUT_DIR/0_output_$FILE_NAME.json > $OUT_DIR/1_converted_$FILE_NAME.txt +# sed 's/null//g' $OUT_DIR/1_converted_$FILE_NAME.txt > $OUT_DIR/2_without_nulls_$FILE_NAME.txt +# sed 's/^ *//; s/ *$//; /^$/d' $OUT_DIR/2_without_nulls_$FILE_NAME.txt > $OUT_DIR/3_without_nulls_$FILE_NAME.txt +# sed 's/\"//g' $OUT_DIR/3_without_nulls_$FILE_NAME.txt > $OUT_DIR/4_phrases_$FILE_NAME.txt ls -l $OUT_DIR >> log_ydl.txt echo " $(date) ###### end conversion __ $1 __ $2" >> log_ydl.txt