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

119
example.ipynb
View File

@@ -1,123 +1,125 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "a2cd4050",
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"outputs": [],
"source": [
"from transcribe import transcribe"
"# Local Transcribe with Whisper\n",
"## Example"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "24e1d24e",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Help on function transcribe in module transcribe:\n",
"Help on function transcribe in module src._LocalTranscribe:\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",
"transcribe(path, glob_file, model=None, language=None, verbose=False)\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"
]
}
],
"source": [
"# Import the modules and get the docstring\n",
"from src._LocalTranscribe import transcribe, get_path\n",
"help(transcribe)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "e52477fb",
"execution_count": 2,
"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"
"# Set the variables\n",
"path='sample_audio/'# Folder path\n",
"model='small' # Model size\n",
"language= None # Preset language, None for automatic detection\n",
"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",
"execution_count": 4,
"id": "d66866af",
"execution_count": 3,
"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",
"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",
"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",
"[00:00.000 --> 00:07.000] I'm going to step off the limb now.\n",
"[00:07.000 --> 00:18.000] That's one small step for man.\n",
"[00:18.000 --> 00:24.000] One giant leap for mankind.\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",
"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",
"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",
"Not a valid file, skipping.\n"
]
},
{
"data": {
"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": {},
"output_type": "execute_result"
}
],
"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": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "venv",
"language": "python",
"name": "python3"
},
@@ -132,8 +134,9 @@
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.4"
}
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 5
"nbformat_minor": 2
}