updated version number

CITATION.cff

@@ -5,7 +5,7 @@ authors:
   given-names: "Kristofer Rolf"
   orcid: "https://orcid.org/0000-0002-5322-3350"
 title: "transcribe"
-version: 1.0
+version: 1.1.1
 doi: 10.5281/zenodo.7760511
 date-released: 2023-03-22
 url: "https://github.com/soderstromkr/transcribe"

GUI.py

@@ -0,0 +1,100 @@
+import tkinter as tk
+from tkinter import ttk
+from tkinter import filedialog
+from tkinter import messagebox
+from transcribe import transcribe
+from ttkthemes import ThemedTk
+import whisper 
+import numpy as np
+import glob, os
+
+
+class App:
+    def __init__(self, master):
+        self.master = master
+        master.title("Local Transcribe")
+
+        #style options
+        style = ttk.Style()
+        style.configure('TLabel', font=('Arial', 10), padding=10)
+        style.configure('TEntry', font=('Arial', 10), padding=10)
+        style.configure('TButton', font=('Arial', 10), padding=10)
+        style.configure('TCheckbutton', font=('Arial', 10), padding=10)
+
+        # Folder Path
+        path_frame = ttk.Frame(master, padding=10)
+        path_frame.pack(fill=tk.BOTH)
+        path_label = ttk.Label(path_frame, text="Folder Path:")
+        path_label.pack(side=tk.LEFT, padx=5)
+        self.path_entry = ttk.Entry(path_frame, width=50)
+        self.path_entry.insert(10, 'sample_audio/')
+        self.path_entry.pack(side=tk.LEFT, fill=tk.X, expand=True)
+        browse_button = ttk.Button(path_frame, text="Browse", command=self.browse)
+        browse_button.pack(side=tk.LEFT, padx=5)
+
+        # File Type
+        file_type_frame = ttk.Frame(master, padding=10)
+        file_type_frame.pack(fill=tk.BOTH)
+        file_type_label = ttk.Label(file_type_frame, text="File Type:")
+        file_type_label.pack(side=tk.LEFT, padx=5)
+        self.file_type_entry = ttk.Entry(file_type_frame, width=50)
+        self.file_type_entry.insert(10, 'ogg')
+        self.file_type_entry.pack(side=tk.LEFT, fill=tk.X, expand=True)
+
+        # Model
+        model_frame = ttk.Frame(master, padding=10)
+        model_frame.pack(fill=tk.BOTH)
+        model_label = ttk.Label(model_frame, text="Model:")
+        model_label.pack(side=tk.LEFT, padx=5)
+        self.model_entry = ttk.Entry(model_frame, width=50)
+        self.model_entry.insert(10, 'small')
+        self.model_entry.pack(side=tk.LEFT, fill=tk.X, expand=True)
+
+        # Language (currently disabled)
+        #language_frame = ttk.Frame(master, padding=10)
+        #language_frame.pack(fill=tk.BOTH)
+        #language_label = ttk.Label(language_frame, text="Language:")
+        #language_label.pack(side=tk.LEFT, padx=5)
+        #self.language_entry = ttk.Entry(language_frame, width=50)
+        #self.language_entry.insert(10, np.nan)
+        #self.language_entry.pack(side=tk.LEFT, fill=tk.X, expand=True)
+
+        # Verbose
+        verbose_frame = ttk.Frame(master, padding=10)
+        verbose_frame.pack(fill=tk.BOTH)
+        self.verbose_var = tk.BooleanVar()
+        verbose_checkbutton = ttk.Checkbutton(verbose_frame, text="Verbose", variable=self.verbose_var)
+        verbose_checkbutton.pack(side=tk.LEFT, padx=5)
+
+        # Buttons
+        button_frame = ttk.Frame(master, padding=10)
+        button_frame.pack(fill=tk.BOTH)
+        transcribe_button = ttk.Button(button_frame, text="Transcribe Audio", command=self.transcribe)
+        transcribe_button.pack(side=tk.LEFT, padx=5, pady=10, fill=tk.X, expand=True)
+        quit_button = ttk.Button(button_frame, text="Quit", command=master.quit)
+        quit_button.pack(side=tk.RIGHT, padx=5, pady=10, fill=tk.X, expand=True)
+
+    def browse(self):
+        folder_path = filedialog.askdirectory()
+        self.path_entry.delete(0, tk.END)
+        self.path_entry.insert(0, folder_path)
+
+    def transcribe(self):
+        path = self.path_entry.get()
+        file_type = self.file_type_entry.get()
+        model = self.model_entry.get()
+        #language = self.language_entry.get()
+        language = None # set to auto-detect
+        verbose = self.verbose_var.get()
+
+        # Call the transcribe function with the appropriate arguments
+        result = transcribe(path, file_type, model=model, language=language, verbose=verbose)
+
+        # Show the result in a message box
+        tk.messagebox.showinfo("Finished!", result)
+
+if __name__ == "__main__":
+#    root = tk.Tk()
+    root = ThemedTk(theme="clearlooks")
+    app = App(root) 
+    root.mainloop()

Mac_2_instructions.txt

@@ -0,0 +1,6 @@
+### 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.

README.md

@@ -1,7 +1,7 @@
 ## transcribe
 Simple script that uses OpenAI's Whisper to transcribe audio files from your local folders. 
 ## Note
-This implementation and guide is mostly made for researchers not familiar with programming that want a way to transcribe their files locally, without internet connection, usually required within ethical data practices and frameworks. Two examples are shown, a normal workflow with interent connection. And one in which the model is loaded first, via openai-whisper, and then the transcription can be done without being connected to the internet. 
+This implementation and guide is mostly made for researchers not familiar with programming that want a way to transcribe their files locally, without internet connection, usually required within ethical data practices and frameworks. Two examples are shown, a normal workflow with internet connection. And one in which the model is loaded first, via openai-whisper, and then the transcription can be done without being connected to the internet. There is now also a GUI implementation, read below for more information.  
 
 ### Instructions 
 #### Requirements
@@ -16,15 +16,27 @@ Users might not need to specifically install Transfomers. However, a conda insta
 ```
 pip install -U openai-whisper
 ```
+4. There is an option to run a batch file, which launches a GUI built on TKinter and TTKthemes. If using these options, make sure they are installed in your python build. You can install them via pip.
+```
+pip install tk
+```
+and
+```
+pip install ttkthemes 
+```
 #### Using the script
 This is a simple script with no installation. You can either clone the repository with
 ```
 git clone https://github.com/soderstromkr/transcribe.git
 ```
-and use the example.ipynb template to use the script **OR (for beginners)** download the ```transcribe.py``` file into your work folder. Then you can either import it to another script or notebook for use. I recommend jupyter notebook for new users, see the example below. (Remember to have transcribe.py and example.ipynb in the same working folder).
+and use the example.ipynb template to use the script.
+**OR** download the ```transcribe.py``` file into your work folder. Then you can either import it to another script or notebook for use. I recommend jupyter notebook for new users, see the example below. (Remember to have transcribe.py and example.ipynb in the same working folder). 
+#### 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:  
+![python GUI.py](gui_jpeg.jpg?raw=true)
 
-### Example
-See the [example](example.ipynb) implementation on jupyter notebook. 
 
 [^1]: Advanced users can use ```pip install ffmpeg-python``` but be ready to deal with some [PATH issues](https://stackoverflow.com/questions/65836756/python-ffmpeg-wont-accept-path-why), which I encountered in Windows 11.
 

example.ipynb

@@ -40,7 +40,7 @@
    "outputs": [],
    "source": [
     "path='sample_audio/'#folder path\n",
-    "file_type='ogg' #check your file for file type, will only transcribe files with the file type, 'ogg', 'WAV'\n",
+    "file_type='ogg' #check your file for file type, will only transcribe those files\n",
     "model='medium' #'small', 'medium', 'large' (tradeoff between speed and accuracy)\n",
     "language= None #tries to auto-detect, other options include 'English', 'Spanish', etc...\n",
     "verbose = True # prints output while transcribing, False to deactivate"

example_no_internet.ipynb

@@ -132,7 +132,7 @@
    "outputs": [],
    "source": [
     "path='sample_audio/'#folder path\n",
-    "file_type='ogg' #check your file for file type, will only transcribe files with the file type, 'ogg', 'WAV'\n",
+    "file_type='ogg' #check your file for file type, will only transcribe those files\n",
     "model='medium' #'small', 'medium', 'large' (tradeoff between speed and accuracy)\n",
     "language= None #tries to auto-detect, other options include 'English', 'Spanish', etc...\n",
     "verbose = True # prints output while transcribing, False to deactivate"

run_Mac_1.sh

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

run_Mac_2.command

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

run_Windows.bat

@@ -0,0 +1,5 @@
+@echo off
+echo Starting...
+call conda activate venv
+REM OPTION 2 : (KEEP TEXT WITHIN QUOTES AND CHANGE USERNAME) "C:/Users/user/Anaconda3/condabin/activate.bat"
+call python GUI.py

sample_audio/transcriptions/Armstrong_Small_Step.txt

@@ -1,3 +1,5 @@
 Armstrong_Small_Step
 In seconds:
-[0.00 --> 24.00]: That's one small step for man, one giant leap for mankind.
+[0.00 --> 7.00]: I'm going to step off the limb now.
+[7.00 --> 18.00]: That's one small step for man.
+[18.00 --> 24.00]: One giant leap for mankind.

sample_audio/transcriptions/Axel_Pettersson_röstinspelning.txt

@@ -1,3 +1,4 @@
 Axel_Pettersson_röstinspelning
 In seconds:
-[0.00 --> 16.00]: Hej, jag heter Axel Pettersson, jag föddes i Örebro 1976. Jag har varit Wikipedia sen 2008 och jag har översatt röstintroduktionsprojektet till svenska.
+[0.00 --> 6.14]: Hej, jag heter Axel Pettersson. Jag följer bror 1976.
+[6.40 --> 15.10]: Jag har varit vikerpedjan sen 2008 och jag har översatt röstintroduktionsprojektet till svenska.

transcribe.py

@@ -1,21 +1,20 @@
 import whisper 
 import glob, os
 
-def transcribe(path, file_type, model=None, language=None, verbose=True):
+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'''
 
     try:
-        os.mkdir('{}transcriptions'.format(path))
+        os.mkdir('{}/transcriptions'.format(path))
     except FileExistsError:
         pass
     
     glob_file = glob.glob(path+'/*{}'.format(file_type))
-    path = path
         
-    print('Using {} model, you can change this by specifying model="medium" for example'.format(model))
-    print('Only looking for file type {}, you can change this by specifying file_type="mp3"'.format(file_type))    
-    print('Expecting {} language, you can change this by specifying language="English". None will try to auto-detect'.format(language))
-    print('Verbosity is {}. If TRUE it will print out the text as it is transcribed, you can turn this off by setting verbose=False'.format(verbose))
+    print('Using {} model'.format(model))
+    print('File type is {}'.format(file_type))    
+    print('Language is being detected automatically for each file')
+    print('Verbosity is set to {}'.format(verbose))
     print('\nThere are {} {} files in path: {}\n\n'.format(len(glob_file), file_type, path))
     
     print('Loading model...')
@@ -29,7 +28,7 @@ def transcribe(path, file_type, model=None, language=None, verbose=True):
         result = model.transcribe(
             file, 
             language=language, 
-            verbose=True
+            verbose=verbose
         )
         start=[]
         end=[]
@@ -39,7 +38,7 @@ def transcribe(path, file_type, model=None, language=None, verbose=True):
             end.append(result['segments'][i]['end'])
             text.append(result['segments'][i]['text'])
         
-        with open("{}transcriptions/{}.txt".format(path,title), 'w', encoding='utf-8') as file:
+        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'])):
@@ -47,4 +46,4 @@ def transcribe(path, file_type, model=None, language=None, verbose=True):
                 
         print('\nFinished file number {}.\n\n\n'.format(idx+1))
 
-    return 'Finished transcription, files can be found in {}transcriptions'.format(path)    
+    return 'Finished transcription, files can be found in {}/transcriptions'.format(path)