Update README.md

README.md formatting suggestions

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_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

@@ -1,30 +1,71 @@
-## transcribe
+## Local Transcribe
-Simple script that uses OpenAI's Whisper to transcribe audio files from your local folders. 
+
+Local Transcribe uses OpenAI's Whisper to transcribe audio files from your local folders, creating text files on disk. 
+
 ## 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
-1. This script was made and tested in an Anaconda environment with python 3.10. I recommend this method if you're not familiar with python.
+
+1. This script was made and tested in an Anaconda environment with Python 3.10. I recommend this method if you're not familiar with Python.
 See [here](https://docs.anaconda.com/anaconda/install/index.html) for instructions. You might need administrator rights. 
+
 2. Whisper requires some additional libraries. The [setup](https://github.com/openai/whisper#setup) page states: "The codebase also depends on a few Python packages, most notably HuggingFace Transformers for their fast tokenizer implementation and ffmpeg-python for reading audio files."
-Users might not need to specifically install Transfomers. However, a conda installation might be needed for ffmepg[^1], which takes care of setting up PATH variables. From the anaconda prompt, type or copy the following:
+Users might not need to specifically install Transfomers. However, a conda installation might be needed for ffmpeg[^1], which takes care of setting up PATH variables. From the anaconda prompt, type or copy the following:
+
 ```
 conda install -c conda-forge ffmpeg-python
 ```
+
 3. The main functionality comes from openai-whisper. See their [page](https://github.com/openai/whisper) for details. As of 2023-03-22 you can install via:
+
 ```
 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
+
+This is a simple script with no installation. You can download the zip folder and extract it to your preferred working folder.
+
+![](Picture1.png)  
+
+Or by cloning 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).
 
-### Example
+
-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. 
+#### 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_Windows.bat (for Windows users), 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)
+
+or this, on a Mac, by running `python GUI.py` or `python3 GUI.py`:
+
+![python GUI Mac.py](gui-mac.png)
 
 [^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.
 

run_Windows.bat

@@ -0,0 +1,5 @@
+@echo off
+echo Starting...
+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

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 +1,27 @@
 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=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))
+    #if torch.cuda.is_available():
-    print('Only looking for file type {}, you can change this by specifying file_type="mp3"'.format(file_type))    
+    #    generator = torch.Generator('cuda').manual_seed(42)
-    print('Expecting {} language, you can change this by specifying language="English". None will try to auto-detect'.format(language))
+    #else:
-    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))
+    #    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')
+    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...')
@@ -29,22 +35,22 @@ def transcribe(path, file_type, model=None, language=None, verbose=True):
         result = model.transcribe(
             file, 
             language=language, 
-            verbose=True
+            verbose=verbose
         )
         start=[]
         end=[]
         text=[]
         for i in range(len(result['segments'])):
-            start.append(result['segments'][i]['start'])
+            start.append(str(datetime.timedelta(seconds=(result['segments'][i]['start']))))
-            end.append(result['segments'][i]['end'])
+            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:
+        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))
 
-    return 'Finished transcription, files can be found in {}transcriptions'.format(path)    
+    return 'Finished transcription, files can be found in {}/transcriptions'.format(path)