43 lines
1.6 KiB
Python
43 lines
1.6 KiB
Python
from speechlib import Transcriptor
|
|
from configparser import ConfigParser
|
|
import os
|
|
|
|
def str2bool(v):
|
|
return v.lower() in ("yes", "true", "t", "1")
|
|
|
|
config = ConfigParser()
|
|
config.read('config.ini')
|
|
audiofolder = config.get('FILE', 'audiofolder')
|
|
access_token = config.get('FILE', 'accesstoken')
|
|
voicefolder = config.get('FILE', 'voicefolder')
|
|
language = "id"
|
|
quantization = str2bool(config.get('FILE', 'quantization'))
|
|
modelSize = "medium"
|
|
|
|
### load the audio file in audio folder ###
|
|
current_dir = os.getcwd()
|
|
audio_dir = current_dir + audiofolder
|
|
output_dir = os.path.join(current_dir, "output")
|
|
if not os.path.exists(audio_dir):
|
|
os.makedirs(audio_dir)
|
|
print(f"Current directory: {current_dir}")
|
|
print(f"Audio directory: {audio_dir}")
|
|
print(f"Output directory: {output_dir}")
|
|
if not os.path.exists(output_dir):
|
|
os.makedirs(output_dir)
|
|
|
|
### Loop for each audio file in the audio folder ###
|
|
for filename in os.listdir(audio_dir):
|
|
if filename.lower().endswith(".mp3") or filename.lower().endswith(".wav"):
|
|
audiofile = os.path.join(audio_dir, filename)
|
|
print(f"Audio file: {audiofile}")
|
|
audiofilewithoutextension = audiofile.split(".mp3")[0].split(".wav")[0]
|
|
filenamewithoutextension = filename.split(".mp3")[0].split(".wav")[0]
|
|
filepath = os.path.join(output_dir, os.path.basename(audiofilewithoutextension).split('/')[-1]+".txt")
|
|
print(f"Output file: {filepath}")
|
|
filename = open(filepath, "w")
|
|
|
|
### transcribe ###
|
|
transcriptor = Transcriptor(audiofile, output_dir, language, modelSize, access_token, voicefolder, quantization)
|
|
res = transcriptor.faster_whisper()
|
|
|