Update transcribe.py

better time keeping

Mac_2_instructions.txt

@@ -1,6 +0,0 @@
-### Steps to make command file executable 
-To make a file executable on a Mac, you need to open a terminal window in the directory where the file is located. Then run the following command: 
-
-chmod +x run_MAC_2.command
-
-After running this command, the file should be marked as executable and you should be able to run it by double-clicking on it.

Mac_instructions.txt

@@ -0,0 +1,5 @@
+### How to run on Mac
+Unfortunately, I have not found a permament solution for this, not being a Mac user has limited the ways I can test this. For now, these are the recommended steps for a beginner user:
+1. Open a terminal and navigate to the root folder (transcribe-main if you downloaded the folder). You can also right-click (or equivalent) on the root folder to open a Terminal within the folder.
+2. Run the following command: 
+python GUI.py

README.md

@@ -34,7 +34,7 @@ and use the example.ipynb template to use the script.
 #### Example with jupyter notebook 
 See [example](example.ipynb) for an implementation on jupyter notebook, also added an example for a simple [workaround](example_no_internet.ipynb) to transcribe while offline. 
 #### Using the GUI 
-You can also run the GUI version from your terminal running ```python GUI.py``` or with the batch file called run_gui.bat, just make sure to add your conda path to it. If you want to download a model first, and then go offline for transcription, I recommend running the model with the default sample folder, which will download the model locally. The GUI should look like this:  
+You can also run the GUI version from your terminal running ```python GUI.py``` or with the batch file called run_Windows.bat (for Windows user, Mac users should read the text file for instructions), just make sure to add your conda path to it. If you want to download a model first, and then go offline for transcription, I recommend running the model with the default sample folder, which will download the model locally. The GUI should look like this:  
 ![python GUI.py](gui_jpeg.jpg?raw=true)
 
 

run_Mac_1.sh

@@ -1,4 +0,0 @@
-#!/bin/bash
-echo Starting...
-conda activate venv
-python -u GUI.py

run_Mac_2.command

@@ -1,3 +0,0 @@
-#!/bin/bash
-echo Running Script
-python -u GUI.py

run_Windows.bat

@@ -1,5 +1,5 @@
 @echo off
 echo Starting...
-call conda activate venv
+call conda activate base
 REM OPTION 2 : (KEEP TEXT WITHIN QUOTES AND CHANGE USERNAME) "C:/Users/user/Anaconda3/condabin/activate.bat"
 call python GUI.py

transcribe.py

@@ -1,5 +1,7 @@
 import whisper 
 import glob, os
+#import torch #uncomment if using torch with cuda, below too
+import datetime
 
 def transcribe(path, file_type, model=None, language=None, verbose=False):
     '''Implementation of OpenAI's whisper model. Downloads model, transcribes audio files in a folder and returns the text files with transcriptions'''
@@ -11,6 +13,11 @@ def transcribe(path, file_type, model=None, language=None, verbose=False):
     
     glob_file = glob.glob(path+'/*{}'.format(file_type))
 
+    #if torch.cuda.is_available():
+    #    generator = torch.Generator('cuda').manual_seed(42)
+    #else:
+    #    generator = torch.Generator().manual_seed(42)
+        
     print('Using {} model'.format(model))
     print('File type is {}'.format(file_type))    
     print('Language is being detected automatically for each file')
@@ -34,15 +41,15 @@ def transcribe(path, file_type, model=None, language=None, verbose=False):
         end=[]
         text=[]
         for i in range(len(result['segments'])):
-            start.append(result['segments'][i]['start'])
-            end.append(result['segments'][i]['end'])
+            start.append(str(datetime.timedelta(seconds=(result['segments'][i]['start']))))
+            end.append(str(datetime.timedelta(seconds=(result['segments'][i]['end']))))
             text.append(result['segments'][i]['text'])
         
         with open("{}/transcriptions/{}.txt".format(path,title), 'w', encoding='utf-8') as file:
             file.write(title)
             file.write('\nIn seconds:')
             for i in range(len(result['segments'])):
-                file.writelines('\n[{:.2f} --> {:.2f}]:{}'.format(start[i], end[i], text[i]))
+                file.writelines('\n[{} --> {}]:{}'.format(start[i], end[i], text[i]))
                 
         print('\nFinished file number {}.\n\n\n'.format(idx+1))