kobim/whisper-local-transcribe
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Complete rework for GUI, experimental EXE file and other minor changes, see readme for more info

Browse Source
This commit is contained in:
Kristofer Söderström
2023-06-30 16:11:59 +02:00
parent b765ff6bc6
commit d96333a5a7
19 changed files with 386 additions and 520 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
CITATION.cff
View File

@@ -4,8 +4,8 @@ authors:
- family-names: "Söderström" - family-names: "Söderström"
given-names: "Kristofer Rolf" given-names: "Kristofer Rolf"
orcid: "https://orcid.org/0000-0002-5322-3350" orcid: "https://orcid.org/0000-0002-5322-3350"
title: "transcribe" title: "Local Transcribe"
version: 1.1.1 version: 1.2
doi: 10.5281/zenodo.7760511 doi: 10.5281/zenodo.7760510
date-released: 2023-03-22 date-released: 2023-03-22
url: "https://github.com/soderstromkr/transcribe" url: "https://github.com/soderstromkr/transcribe"

100
GUI.py
View File

@@ -1,100 +0,0 @@
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()

9
Mac_instructions.md Normal file
View File

@@ -0,0 +1,9 @@
### 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.
#### Recommended steps
1. Open a terminal and navigate to the root folder (the downloaded the folder).
1. You can also right-click (or equivalent) on the root folder to open a Terminal within the folder.
2. Run the following command:
```
python main.py
```

5
Mac_instructions.txt
View File

@@ -1,5 +0,0 @@
### 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

122
README.md
View File

@@ -1,71 +1,75 @@
## Local Transcribe ## Local Transcribe with Whisper
Local Transcribe with Whisper is a user-friendly desktop application that allows you to transcribe audio and video files using the Whisper ASR system. This application provides a graphical user interface (GUI) built with Python and the Tkinter library, making it easy to use even for those not familiar with programming.
Local Transcribe uses OpenAI's Whisper to transcribe audio files from your local folders, creating text files on disk. ## New in version 1.2!
1. Simpler usage:
1. File type: You no longer need to specify file type. The program will only transcribe elligible files.
2. Language: Added option to specify language, which might help in some cases. Clear the default text to run automatic language recognition.
3. Model selection: Now a dropdown option that includes most models for typical use.
2. New and improved GUI.
![python GUI.py](images/gui-windows.png)
3. Executable: On Windows and don't want to install python? Try the Exe file! See below for instructions (Experimental)
## Note ## Features
* Select the folder containing the audio or video files you want to transcribe. Tested with m4a video.
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. * Choose the language of the files you are transcribing. You can either select a specific language or let the application automatically detect the language.
* Select the Whisper model to use for the transcription. Available models include "base.en", "base", "small.en", "small", "medium.en", "medium", and "large". Models with .en ending are better if you're transcribing English, especially the base and small models.
### Instructions * Enable the verbose mode to receive detailed information during the transcription process.
* Monitor the progress of the transcription with the progress bar and terminal.
#### Requirements * Confirmation dialog before starting the transcription to ensure you have selected the correct folder.
* View the transcribed text in a message box once the transcription is completed.
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 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 download the zip folder and extract it to your preferred working folder.
## Installation
### Get the files
Download the zip folder and extract it to your preferred working folder.
![](Picture1.png) ![](Picture1.png)
Or by cloning the repository with: Or by cloning the repository with:
``` ```
git clone https://github.com/soderstromkr/transcribe.git git clone https://github.com/soderstromkr/transcribe.git
``` ```
### Executable Version **(Experimental. Windows only)**
The executable version of Local Transcribe with Whisper is a standalone program and should work out of the box. This experimental version is available if you have Windows, and do not have (or don't want to install) python and additional dependencies. However, it requires more disk space (around 1Gb), has no GPU acceleration and has only been lightly tested for bugs, etc. Let me know if you run into any issues!
1. Download the project folder. As the image above shows.
2. Navigate to build.
3. Unzip the folder (get a coffee or a tea, this might take a while depending on your computer)
3. Run the executable (app.exe) file.
### Python Version **(any platform including Mac users)**
This is recommended if you don't have Windows. Have Windows and use python, or want to use GPU acceleration (Pytorch and Cuda) for faster transcriptions. I would generally recommend this method anyway, but I can understand not everyone wants to go through the installation process for Python, Anaconda and the other required packages.
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 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. To run the app 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 tkinter
```
and
```
pip install customtkinter
```
5. Run the app:
1. For **Windows**: In the same folder as the *app.py* file, run the app from terminal by running ```python app.py``` or with the batch file called run_Windows.bat (for Windows users), which assumes you have conda installed and in the base environment (This is for simplicity, but users are usually adviced to create an environment, see [here](https://conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html#creating-an-environment-with-commands) for more info) just make sure you have the correct environment (right click on the file and press edit to make any changes). 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.
2. For **Mac**: Haven't figured out a better way to do this, see [the instructions here](Mac_instructions.txt)
## Usage
1. When launched, the app will also open a terminal that shows some additional information.
2. Select the folder containing the audio or video files you want to transcribe by clicking the "Browse" button next to the "Folder" label. This will open a file dialog where you can navigate to the desired folder. Remember, you won't be choosing individual files but whole folders!
3. Enter the desired language for the transcription in the "Language" field. You can either select a language or leave it blank to enable automatic language detection.
4. Choose the Whisper model to use for the transcription from the dropdown list next to the "Model" label.
5. Enable the verbose mode by checking the "Verbose" checkbox if you want to receive detailed information during the transcription process.
6. Click the "Transcribe" button to start the transcription. The button will be disabled during the process to prevent multiple transcriptions at once.
7. Monitor the progress of the transcription with the progress bar.
8. Once the transcription is completed, a message box will appear displaying the transcribed text. Click "OK" to close the message box.
9. You can run the application again or quit the application at any time by clicking the "Quit" button.
## Jupyter Notebook
#### Example with Jupyter Notebook Don't want fancy EXEs or GUIs? Use the function as is. See [example](example.ipynb) for an implementation on 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. [^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.

133
app.py Normal file
View File

@@ -0,0 +1,133 @@
import tkinter as tk
from tkinter import ttk
from tkinter import filedialog
from tkinter import messagebox
from src._LocalTranscribe import transcribe, get_path
import customtkinter
import threading
from colorama import Back, Fore
import colorama
colorama.init(autoreset=True)
customtkinter.set_appearance_mode("System")
customtkinter.set_default_color_theme("blue") # Themes: blue (default), dark-blue, green
firstclick = True
class App:
def __init__(self, master):
print(Back.CYAN + "Welcome to Local Transcribe with Whisper!\U0001f600\nCheck back here to see some output from your transcriptions.\nDon't worry, they will also be saved on the computer!\U0001f64f")
self.master = master
# Change font
font = ('Roboto', 13, 'bold') # Change the font and size here
font_b = ('Roboto', 12) # Change the font and size here
# Folder Path
path_frame = customtkinter.CTkFrame(master)
path_frame.pack(fill=tk.BOTH, padx=10, pady=10)
customtkinter.CTkLabel(path_frame, text="Folder:", font=font).pack(side=tk.LEFT, padx=5)
self.path_entry = customtkinter.CTkEntry(path_frame, width=50, font=font_b)
self.path_entry.pack(side=tk.LEFT, fill=tk.X, expand=True)
customtkinter.CTkButton(path_frame, text="Browse", command=self.browse, font=font).pack(side=tk.LEFT, padx=5)
# Language frame
#thanks to pommicket from Stackoverflow for this fix
def on_entry_click(event):
"""function that gets called whenever entry is clicked"""
global firstclick
if firstclick: # if this is the first time they clicked it
firstclick = False
self.language_entry.delete(0, "end") # delete all the text in the entry
language_frame = customtkinter.CTkFrame(master)
language_frame.pack(fill=tk.BOTH, padx=10, pady=10)
customtkinter.CTkLabel(language_frame, text="Language:", font=font).pack(side=tk.LEFT, padx=5)
self.language_entry = customtkinter.CTkEntry(language_frame, width=50, font=('Roboto', 12, 'italic'))
self.language_entry.insert(0, 'Select language or clear to detect automatically')
self.language_entry.bind('<FocusIn>', on_entry_click)
self.language_entry.pack(side=tk.LEFT, fill=tk.X, expand=True)
# Model frame
models = ['base.en', 'base', 'small.en',
'small', 'medium.en', 'medium', 'large']
model_frame = customtkinter.CTkFrame(master)
model_frame.pack(fill=tk.BOTH, padx=10, pady=10)
customtkinter.CTkLabel(model_frame, text="Model:", font=font).pack(side=tk.LEFT, padx=5)
# ComboBox frame
self.model_combobox = customtkinter.CTkComboBox(
model_frame, width=50, state="readonly",
values=models, font=font_b)
self.model_combobox.set(models[1]) # Set the default value
self.model_combobox.pack(side=tk.LEFT, fill=tk.X, expand=True)
# Verbose frame
verbose_frame = customtkinter.CTkFrame(master)
verbose_frame.pack(fill=tk.BOTH, padx=10, pady=10)
self.verbose_var = tk.BooleanVar()
customtkinter.CTkCheckBox(verbose_frame, text="Output transcription to terminal", variable=self.verbose_var, font=font).pack(side=tk.LEFT, padx=5)
# Progress Bar
self.progress_bar = ttk.Progressbar(master, length=200, mode='indeterminate')
# Button actions frame
button_frame = customtkinter.CTkFrame(master)
button_frame.pack(fill=tk.BOTH, padx=10, pady=10)
self.transcribe_button = customtkinter.CTkButton(button_frame, text="Transcribe", command=self.start_transcription, font=font)
self.transcribe_button.pack(side=tk.LEFT, padx=5, pady=10, fill=tk.X, expand=True)
customtkinter.CTkButton(button_frame, text="Quit", command=master.quit, font=font).pack(side=tk.RIGHT, padx=5, pady=10, fill=tk.X, expand=True)
# Helper functions
# Browsing
def browse(self):
folder_path = filedialog.askdirectory()
self.path_entry.delete(0, tk.END)
self.path_entry.insert(0, folder_path)
# Start transcription
def start_transcription(self):
# Disable transcribe button
self.transcribe_button.configure(state=tk.DISABLED)
# Start a new thread for the transcription process
threading.Thread(target=self.transcribe_thread).start()
# Threading
def transcribe_thread(self):
path = self.path_entry.get()
model = self.model_combobox.get()
language = self.language_entry.get() or None
verbose = self.verbose_var.get()
# Show progress bar
self.progress_bar.pack(fill=tk.X, padx=5, pady=5)
self.progress_bar.start()
# Setting path and files
glob_file = get_path(path)
info_path = 'I will transcribe all eligible audio/video files in the path: {}\n\nContinue?'.format(path)
answer = messagebox.askyesno("Confirmation", info_path)
if not answer:
self.progress_bar.stop()
self.progress_bar.pack_forget()
self.transcribe_button.configure(state=tk.NORMAL)
return
# Start transcription
error_language = 'https://github.com/openai/whisper#available-models-and-languages'
try:
output_text = transcribe(path, glob_file, model, language, verbose)
except UnboundLocalError:
messagebox.showinfo("Files not found error!", 'Nothing found, choose another folder.')
pass
except ValueError:
messagebox.showinfo("Language error!", 'See {} for supported languages'.format(error_language))
# Hide progress bar
self.progress_bar.stop()
self.progress_bar.pack_forget()
# Enable transcribe button
self.transcribe_button.configure(state=tk.NORMAL)
# Recover output text
try:
messagebox.showinfo("Finished!", output_text)
except UnboundLocalError:
pass
if __name__ == "__main__":
# Setting custom themes
root = customtkinter.CTk()
root.title("Local Transcribe with Whisper")
# Geometry
width,height = 450,275
root.geometry('{}x{}'.format(width,height))
# Icon
root.iconbitmap('images/icon.ico')
# Run
app = App(root)
root.mainloop()

20
build_setup.py Normal file
View File

@@ -0,0 +1,20 @@
from cx_Freeze import setup, Executable
build_exe_options = {
"packages": ['whisper','tkinter','customtkinter']
}
executables = (
[
Executable(
"app.py",
icon='images/icon.ico',
)
]
)
setup(
name="Local Transcribe with Whisper",
version="1.2",
author="Kristofer Rolf Söderström",
options={"build_exe":build_exe_options},
executables=executables
)

119
example.ipynb
View File

@@ -1,123 +1,125 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "code", "attachments": {},
"execution_count": 1, "cell_type": "markdown",
"id": "a2cd4050",
"metadata": {}, "metadata": {},
"outputs": [],
"source": [ "source": [
"from transcribe import transcribe" "# Local Transcribe with Whisper\n",
"## Example"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 1,
"id": "24e1d24e",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Help on function transcribe in module transcribe:\n", "Help on function transcribe in module src._LocalTranscribe:\n",
"\n", "\n",
"transcribe(path, file_type, model=None, language=None, verbose=True)\n", "transcribe(path, glob_file, model=None, language=None, verbose=False)\n",
" Implementation of OpenAI's whisper model. Downloads model, transcribes audio files in a folder and returns the text files with transcriptions\n", " Transcribes audio files in a specified folder using OpenAI's Whisper model.\n",
" \n",
" Args:\n",
" path (str): Path to the folder containing the audio files.\n",
" glob_file (list): List of audio file paths to transcribe.\n",
" model (str, optional): Name of the Whisper model to use for transcription.\n",
" Defaults to None, which uses the default model.\n",
" language (str, optional): Language code for transcription. Defaults to None,\n",
" which enables automatic language detection.\n",
" verbose (bool, optional): If True, enables verbose mode with detailed information\n",
" during the transcription process. Defaults to False.\n",
" \n",
" Returns:\n",
" str: A message indicating the result of the transcription process.\n",
" \n",
" Raises:\n",
" RuntimeError: If an invalid file is encountered, it will be skipped.\n",
" \n",
" Notes:\n",
" - The function downloads the specified model if not available locally.\n",
" - The transcribed text files will be saved in a \"transcriptions\" folder\n",
" within the specified path.\n",
"\n" "\n"
] ]
} }
], ],
"source": [ "source": [
"# Import the modules and get the docstring\n",
"from src._LocalTranscribe import transcribe, get_path\n",
"help(transcribe)" "help(transcribe)"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 2,
"id": "e52477fb",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"path='sample_audio/'#folder path\n", "# Set the variables\n",
"file_type='ogg' #check your file for file type, will only transcribe those files\n", "path='sample_audio/'# Folder path\n",
"model='medium' #'small', 'medium', 'large' (tradeoff between speed and accuracy)\n", "model='small' # Model size\n",
"language= None #tries to auto-detect, other options include 'English', 'Spanish', etc...\n", "language= None # Preset language, None for automatic detection\n",
"verbose = True # prints output while transcribing, False to deactivate" "verbose = True # Output transcription in realtime\n",
"\n",
"# Get glob file, additional step for app version.\n",
"\n",
"glob_file = get_path(path)"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 3,
"id": "d66866af",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Using medium model, you can change this by specifying model=\"medium\" for example\n",
"Only looking for file type ogg, you can change this by specifying file_type=\"mp3\"\n",
"Expecting None language, you can change this by specifying language=\"English\". None will try to auto-detect\n",
"Verbosity is True. If TRUE it will print out the text as it is transcribed, you can turn this off by setting verbose=False\n",
"\n",
"There are 2 ogg files in path: sample_audio/\n",
"\n",
"\n",
"Loading model...\n",
"Transcribing file number number 1: Armstrong_Small_Step\n",
"Model and file loaded...\n",
"Starting transcription...\n",
"\n", "\n",
"Trying to transcribe file named: Armstrong_Small_Step🕐\n",
"Detecting language using up to the first 30 seconds. Use `--language` to specify the language\n", "Detecting language using up to the first 30 seconds. Use `--language` to specify the language\n",
"Detected language: English\n", "Detected language: English\n",
"[00:00.000 --> 00:24.000] That's one small step for man, one giant leap for mankind.\n", "[00:00.000 --> 00:07.000] I'm going to step off the limb now.\n",
"\n", "[00:07.000 --> 00:18.000] That's one small step for man.\n",
"Finished file number 1.\n", "[00:18.000 --> 00:24.000] One giant leap for mankind.\n",
"\n",
"\n",
"\n",
"Transcribing file number number 2: Axel_Pettersson_röstinspelning\n",
"Model and file loaded...\n",
"Starting transcription...\n",
"\n", "\n",
"Trying to transcribe file named: Axel_Pettersson_röstinspelning🕐\n",
"Detecting language using up to the first 30 seconds. Use `--language` to specify the language\n", "Detecting language using up to the first 30 seconds. Use `--language` to specify the language\n",
"Detected language: Swedish\n", "Detected language: Swedish\n",
"[00:00.000 --> 00:16.000] Hej, jag heter Axel Pettersson, jag föddes i Örebro 1976. Jag har varit Wikipedia sen 2008 och jag har översatt röstintroduktionsprojektet till svenska.\n", "[00:00.000 --> 00:06.140] Hej, jag heter Axel Pettersson. Jag följer bror 1976.\n",
"[00:06.400 --> 00:15.100] Jag har varit vikerpedjan sen 2008 och jag har översatt röstintroduktionsprojektet till svenska.\n",
"\n", "\n",
"Finished file number 2.\n", "Trying to transcribe file named: readme🕐\n",
"Not a valid file, skipping.\n",
"\n", "\n",
"\n", "Trying to transcribe file named: transcriptions🕐\n",
"\n" "Not a valid file, skipping.\n"
] ]
}, },
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"'Finished transcription, files can be found in sample_audio/transcriptions'" "'Finished transcription, 2 files can be found in sample_audio//transcriptions'"
] ]
}, },
"execution_count": 4, "execution_count": 3,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"source": [ "source": [
"transcribe(path, file_type, model, language, verbose)" "# Run the script\n",
"transcribe(path, glob_file, model, language, verbose)"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0bc67265",
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "venv",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@@ -132,8 +134,9 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.10.4" "version": "3.10.4"
} },
"orig_nbformat": 4
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 5 "nbformat_minor": 2
} }

231
example_no_internet.ipynb
View File

@@ -1,231 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "eba9e610",
"metadata": {},
"source": [
"A simple way to avoid being connected while transcribing is to first load the model version you want to use. See [here](https://github.com/openai/whisper/blob/main/README.md#available-models-and-languages) for more info."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "85cd2d12",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Whisper(\n",
" (encoder): AudioEncoder(\n",
" (conv1): Conv1d(80, 1024, kernel_size=(3,), stride=(1,), padding=(1,))\n",
" (conv2): Conv1d(1024, 1024, kernel_size=(3,), stride=(2,), padding=(1,))\n",
" (blocks): ModuleList(\n",
" (0-23): 24 x ResidualAttentionBlock(\n",
" (attn): MultiHeadAttention(\n",
" (query): Linear(in_features=1024, out_features=1024, bias=True)\n",
" (key): Linear(in_features=1024, out_features=1024, bias=False)\n",
" (value): Linear(in_features=1024, out_features=1024, bias=True)\n",
" (out): Linear(in_features=1024, out_features=1024, bias=True)\n",
" )\n",
" (attn_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
" (mlp): Sequential(\n",
" (0): Linear(in_features=1024, out_features=4096, bias=True)\n",
" (1): GELU(approximate='none')\n",
" (2): Linear(in_features=4096, out_features=1024, bias=True)\n",
" )\n",
" (mlp_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
" )\n",
" (ln_post): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
" (decoder): TextDecoder(\n",
" (token_embedding): Embedding(51865, 1024)\n",
" (blocks): ModuleList(\n",
" (0-23): 24 x ResidualAttentionBlock(\n",
" (attn): MultiHeadAttention(\n",
" (query): Linear(in_features=1024, out_features=1024, bias=True)\n",
" (key): Linear(in_features=1024, out_features=1024, bias=False)\n",
" (value): Linear(in_features=1024, out_features=1024, bias=True)\n",
" (out): Linear(in_features=1024, out_features=1024, bias=True)\n",
" )\n",
" (attn_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
" (cross_attn): MultiHeadAttention(\n",
" (query): Linear(in_features=1024, out_features=1024, bias=True)\n",
" (key): Linear(in_features=1024, out_features=1024, bias=False)\n",
" (value): Linear(in_features=1024, out_features=1024, bias=True)\n",
" (out): Linear(in_features=1024, out_features=1024, bias=True)\n",
" )\n",
" (cross_attn_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
" (mlp): Sequential(\n",
" (0): Linear(in_features=1024, out_features=4096, bias=True)\n",
" (1): GELU(approximate='none')\n",
" (2): Linear(in_features=4096, out_features=1024, bias=True)\n",
" )\n",
" (mlp_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
" )\n",
" (ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
" )\n",
")"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import whisper\n",
"#change to model size, bigger is more accurate but slower\n",
"whisper.load_model(\"medium\") #base, small, medium, large"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "0d2acd54",
"metadata": {},
"outputs": [],
"source": [
"#after it loads, you can disconnect from the internet and run the rest"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "a2cd4050",
"metadata": {},
"outputs": [],
"source": [
"from transcribe import transcribe"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "24e1d24e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Help on function transcribe in module transcribe:\n",
"\n",
"transcribe(path, file_type, model=None, language=None, verbose=True)\n",
" Implementation of OpenAI's whisper model. Downloads model, transcribes audio files in a folder and returns the text files with transcriptions\n",
"\n"
]
}
],
"source": [
"help(transcribe)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "e52477fb",
"metadata": {},
"outputs": [],
"source": [
"path='sample_audio/'#folder path\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"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "d66866af",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Using medium model, you can change this by specifying model=\"medium\" for example\n",
"Only looking for file type ogg, you can change this by specifying file_type=\"mp3\"\n",
"Expecting None language, you can change this by specifying language=\"English\". None will try to auto-detect\n",
"Verbosity is True. If TRUE it will print out the text as it is transcribed, you can turn this off by setting verbose=False\n",
"\n",
"There are 2 ogg files in path: sample_audio/\n",
"\n",
"\n",
"Loading model...\n",
"Transcribing file number number 1: Armstrong_Small_Step\n",
"Model and file loaded...\n",
"Starting transcription...\n",
"\n",
"Detecting language using up to the first 30 seconds. Use `--language` to specify the language\n",
"Detected language: English\n",
"[00:00.000 --> 00:24.000] That's one small step for man, one giant leap for mankind.\n",
"\n",
"Finished file number 1.\n",
"\n",
"\n",
"\n",
"Transcribing file number number 2: Axel_Pettersson_röstinspelning\n",
"Model and file loaded...\n",
"Starting transcription...\n",
"\n",
"Detecting language using up to the first 30 seconds. Use `--language` to specify the language\n",
"Detected language: Swedish\n",
"[00:00.000 --> 00:16.000] Hej, jag heter Axel Pettersson, jag föddes i Örebro 1976. Jag har varit Wikipedia sen 2008 och jag har översatt röstintroduktionsprojektet till svenska.\n",
"\n",
"Finished file number 2.\n",
"\n",
"\n",
"\n"
]
},
{
"data": {
"text/plain": [
"'Finished transcription, files can be found in sample_audio/transcriptions'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"transcribe(path, file_type, model, language, verbose)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0bc67265",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

BIN
gui_jpeg.jpg
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 29 KiB

0
Picture1.png → images/Picture1.png
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 135 KiB

After

Width:  |  Height:  |  Size: 135 KiB

0
gui-mac.png → images/gui-mac.png
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 324 KiB

After

Width:  |  Height:  |  Size: 324 KiB

BIN
images/gui-windows.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 12 KiB

BIN
images/icon.ico Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.8 KiB

2
run_Windows.bat
View File

@@ -2,4 +2,4 @@
echo Starting... echo Starting...
call conda activate base call conda activate base
REM OPTION 2 : (KEEP TEXT WITHIN QUOTES AND CHANGE USERNAME) "C:/Users/user/Anaconda3/condabin/activate.bat" REM OPTION 2 : (KEEP TEXT WITHIN QUOTES AND CHANGE USERNAME) "C:/Users/user/Anaconda3/condabin/activate.bat"
call python GUI.py call python app.py

7
sample_audio/transcriptions/Armstrong_Small_Step.txt
View File

@@ -1,5 +1,4 @@
Armstrong_Small_Step Armstrong_Small_Step
In seconds: [0:00:00 --> 0:00:07]: And they're still brought to land now.
[0.00 --> 7.00]: I'm going to step off the limb now. [0:00:07 --> 0:00:18]: It's one small step for man.
[7.00 --> 18.00]: That's one small step for man. [0:00:18 --> 0:00:23]: One by a fleet for man time.
[18.00 --> 24.00]: One giant leap for mankind.

6
sample_audio/transcriptions/Axel_Pettersson_röstinspelning.txt
View File

@@ -1,4 +1,4 @@
Axel_Pettersson_röstinspelning Axel_Pettersson_röstinspelning
In seconds: [0:00:00 --> 0:00:06]: Hej, jag heter Raxel Patterson, jag får att se över UR 1976.
[0.00 --> 6.14]: Hej, jag heter Axel Pettersson. Jag följer bror 1976. [0:00:06 --> 0:00:12.540000]: Jag har varit Wikipedia-périonsen 2018 och jag har översat röst-intro-
[6.40 --> 15.10]: Jag har varit vikerpedjan sen 2008 och jag har översatt röstintroduktionsprojektet till svenska. [0:00:12.540000 --> 0:00:15.540000]:-projektet till svenska.

90
src/_LocalTranscribe.py Normal file
View File

@@ -0,0 +1,90 @@
import os
import datetime
from glob import glob
import whisper
from torch import cuda, Generator
import colorama
from colorama import Back,Fore
colorama.init(autoreset=True)
# Get the path
def get_path(path):
glob_file = glob(path + '/*')
return glob_file
# Main function
def transcribe(path, glob_file, model=None, language=None, verbose=False):
"""
Transcribes audio files in a specified folder using OpenAI's Whisper model.
Args:
path (str): Path to the folder containing the audio files.
glob_file (list): List of audio file paths to transcribe.
model (str, optional): Name of the Whisper model to use for transcription.
Defaults to None, which uses the default model.
language (str, optional): Language code for transcription. Defaults to None,
which enables automatic language detection.
verbose (bool, optional): If True, enables verbose mode with detailed information
during the transcription process. Defaults to False.
Returns:
str: A message indicating the result of the transcription process.
Raises:
RuntimeError: If an invalid file is encountered, it will be skipped.
Notes:
- The function downloads the specified model if not available locally.
- The transcribed text files will be saved in a "transcriptions" folder
within the specified path.
"""
# Check for GPU acceleration
if cuda.is_available():
Generator('cuda').manual_seed(42)
else:
Generator().manual_seed(42)
# Load model
model = whisper.load_model(model)
# Start main loop
files_transcripted=[]
for file in glob_file:
title = os.path.basename(file).split('.')[0]
print(Back.CYAN + '\nTrying to transcribe file named: {}\U0001f550'.format(title))
try:
result = model.transcribe(
file,
language=language,
verbose=verbose
)
files_transcripted.append(result)
# Make folder if missing
try:
os.makedirs('{}/transcriptions'.format(path), exist_ok=True)
except FileExistsError:
pass
# Create segments for text files
start = []
end = []
text = []
for segment in result['segments']:
start.append(str(datetime.timedelta(seconds=segment['start'])))
end.append(str(datetime.timedelta(seconds=segment['end'])))
text.append(segment['text'])
# Save files to transcriptions folder
with open("{}/transcriptions/{}.txt".format(path, title), 'w', encoding='utf-8') as file:
file.write(title)
for i in range(len(result['segments'])):
file.write('\n[{} --> {}]:{}'.format(start[i], end[i], text[i]))
# Skip invalid files
except RuntimeError:
print(Fore.RED + 'Not a valid file, skipping.')
pass
# Check if any files were processed.
if len(files_transcripted) > 0:
output_text = 'Finished transcription, {} files can be found in {}/transcriptions'.format(len(files_transcripted), path)
else:
output_text = 'No files elligible for transcription, try adding audio or video files to this folder or choose another folder!'
# Return output text
return output_text

56
transcribe.py
View File

@@ -1,56 +0,0 @@
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'''
try:
os.mkdir('{}/transcriptions'.format(path))
except FileExistsError:
pass
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')
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...')
model = whisper.load_model(model)
for idx,file in enumerate(glob_file):
title = os.path.basename(file).split('.')[0]
print('Transcribing file number number {}: {}'.format(idx+1,title))
print('Model and file loaded...\nStarting transcription...\n')
result = model.transcribe(
file,
language=language,
verbose=verbose
)
start=[]
end=[]
text=[]
for i in range(len(result['segments'])):
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[{} --> {}]:{}'.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)