renamed module

app.py

@@ -1,12 +1,12 @@
 from dash import Dash, dcc, html, dash_table, Input, Output, State, callback
 
 import base64
-from autotranscript.app.qtfaststart import process
+from scraibe.app.qtfaststart import process
-from autotranscript import AutoTranscribe
+from scraibe import AutoTranscribe
 import io
 import subprocess as sp
 import numpy as np
-from autotranscript.audio import SAMPLE_RATE
+from scraibe.audio import SAMPLE_RATE
 
 # Setup auto-transcript
 autot = AutoTranscribe() # whisper_model="tiny", whisper_kwargs={"local" : False}

app2.py

@@ -0,0 +1,317 @@
+"""
+Gradio Audio Transcription App.
+--------------------------------
+
+This module provides an interface to transcribe audio files using the 
+AutoTranscribe model. Users can either upload an audio file or record their speech 
+live for transcription. The application supports multiple languages and provides 
+options to specify the number of speakers and the language of the audio.
+
+Attributes:
+    LANGUAGES (list): A list of supported languages for transcription.
+
+Usage:
+    Run this script to start the Gradio web interface for audio transcription.
+    
+"""
+
+
+import json
+
+import gradio as gr
+from scraibe import AutoTranscribe, Transcript
+
+
+
+theme = gr.themes.Soft(
+    primary_hue="green",
+    secondary_hue='orange',
+    neutral_hue="gray",
+    
+)
+LANGUAGES = [
+    "Afrikaans", "Arabic", "Armenian", "Azerbaijani", "Belarusian",
+    "Bosnian", "Bulgarian", "Catalan", "Chinese", "Croatian",
+    "Czech", "Danish", "Dutch", "English", "Estonian",
+    "Finnish", "French", "Galician", "German", "Greek",
+    "Hebrew", "Hindi", "Hungarian", "Icelandic", "Indonesian",
+    "Italian", "Japanese", "Kannada", "Kazakh", "Korean",
+    "Latvian", "Lithuanian", "Macedonian", "Malay", "Marathi",
+    "Maori", "Nepali", "Norwegian", "Persian", "Polish",
+    "Portuguese", "Romanian", "Russian", "Serbian", "Slovak",
+    "Slovenian", "Spanish", "Swahili", "Swedish", "Tagalog",
+    "Tamil", "Thai", "Turkish", "Ukrainian", "Urdu",
+    "Vietnamese", "Welsh"
+]
+
+class GradioTranscriptionInterface:
+    """
+    Interface handling the interaction between Gradio UI and the Audio Transcription system.
+    """
+
+    def __init__(self, model: AutoTranscribe = AutoTranscribe()):
+        """
+        Initializes the GradioTranscriptionInterface with a transcription model.
+
+        Args:
+            model (AutoTranscribe): Model responsible for audio transcription tasks.
+        """
+        self.model = model
+
+    def auto_transcribe(self, source,
+                        num_speakers : int,
+                        translation : bool,
+                        language : str):
+        """
+        Shortcut method for the AutoTranscribe task.
+
+        Returns:
+            tuple: Transcribed text (str), JSON output (dict)
+        """
+        
+        kwargs = {
+            "num_speakers": num_speakers if num_speakers != 0 else None,
+            "language": language if language != "None" else None,
+            "task": 'translate' if translation else None
+        }
+        
+        try:
+            result = self.model.autotranscribe(source, **kwargs)
+        except ValueError:
+            raise gr.Error("Couldn't detect any speech in the provided audio. \
+                    Please try again!")
+        return str(result), result.get_json()
+
+
+    def transcribe(self, source, translation, language):
+        """
+        Shortcut method for the Transcribe task.
+
+        Returns:
+            str: Transcribed text.
+        """
+        kwargs = {
+            "language": language if language != "None" else None,
+            "task": 'translate' if translation == "Yes" else None
+        }
+        
+        result = self.model.transcribe(source, **kwargs)
+        return str(result)
+
+    def perform_diarisation(self, source, num_speakers):
+        """
+        Shortcut method for the Diarisation task.
+
+        Returns:
+            str: JSON output of diarisation result.
+        """
+        kwargs = {
+            "num_speakers": num_speakers if num_speakers != 0 else None,
+        }
+        
+        
+        try:
+            result = self.model.diarization(source, **kwargs)
+        except ValueError:
+            raise gr.Error("Couldn't detect any speech in the provided audio. \
+                    Please try again!")
+        return json.dumps(result, indent=2)
+
+####
+# Gradio Interface
+####
+
+pipe = GradioTranscriptionInterface()
+
+
+def select_task(choice):
+    if choice == 'Auto Transcribe':
+        
+        return (gr.update(visible = True),
+                gr.update(visible = True),
+                gr.update(visible = True))
+                
+        
+    elif choice == 'Transcribe':
+        
+        return (gr.update(visible = False),
+                gr.update(visible = True),
+                gr.update(visible = True))
+
+        
+    elif choice == 'Diarisation':
+        
+        return (gr.update(visible = True),
+                gr.update(visible = False),
+                gr.update(visible = False))
+    
+def select_origin(choice):
+    if choice == "Upload Audio":
+        
+        return (gr.update(visible = True),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None))
+    
+    elif choice == "Record Audio":
+        
+        return (gr.update(visible = False, value = None),
+                gr.update(visible = True),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None))
+
+    elif choice == "Upload Video":
+        
+        return (gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = True),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None))
+    
+    elif choice == "Record Video":
+        
+        return (gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = True),
+                gr.update(visible = False, value = None))
+        
+    elif choice == "File":
+        
+        return (gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = False, value = None),
+                gr.update(visible = True))
+
+def run_scribe(task, num_speakers, translate, language, audio1, audio2, video1, video2, file_in, progress = gr.Progress(track_tqdm= True)):
+    # get *args which are not None
+    progress(0, desc='Starting task...')
+    source = audio1 or audio2 or video1 or video2 or file_in
+    
+    if task == 'Auto Transcribe':
+        
+        out_str , out_json = pipe.auto_transcribe(source = source,
+                             num_speakers = num_speakers,
+                             translation = translate,
+                             language = language)
+        
+        return (gr.update(value = out_str, visible = True),
+                gr.update(value = out_json, visible = True),
+                gr.update(visible = True),
+                gr.update(visible = True))        
+        
+    elif task == 'Transcribe':
+        
+        out = pipe.transcribe(source = source,
+                             translation = translate,
+                             language = language)
+        
+        return (gr.update(value = out, visible = True),
+                gr.update(value = None, visible = False),
+                gr.update(visible = False),
+                gr.update(visible = False))
+        
+    elif task == 'Diarisation':
+        
+        out = pipe.perform_diarisation(source = source,
+                             num_speakers = num_speakers)
+        
+        return (gr.update(value = None, visible = False),
+                gr.update(value = out, visible = True),
+                gr.update(visible = False),
+                gr.update(visible = False))
+    
+def annotate_output(annoation : str, out_json : dict):
+    # get *args which are not None
+    
+    trans = Transcript.from_json(out_json)
+    trans = trans.annotate(*annoation.split(","))
+
+    return gr.update(value = str(trans)),gr.update(value = trans.get_json())
+    
+    
+with gr.Blocks(theme=theme,title='ScrAIbe: Automatic Audio Transcription') as demo:
+    
+    # Define components
+    header = open("header.html", "r").read()
+    gr.HTML(header,  visible= True, show_label=False)
+    
+    with gr.Row():
+        
+        with gr.Column():
+        
+            task = gr.Radio(["Auto Transcribe", "Transcribe", "Diarisation"], label="Task",
+                            value= 'Auto Transcribe')
+            
+            num_speakers = gr.Number(value=0, label= "Number of speakers (optional)", 
+                            info = "Number of speakers in the audio file. If you don't know,\
+                                leave it at 0.", visible= True)
+            
+            translate = gr.Checkbox(label="Translation", choices=[True, False], value = False,
+                            info="Select 'Yes' to have the output translated into English.",
+                            visible= True)
+            
+            language = gr.Dropdown(LANGUAGES,
+                            label="Language (optional)", value = "None",
+                            info="Language of the audio file. If you don't know,\
+                                leave it at None.", visible= True)
+            
+            input = gr.Radio(["Upload Audio", "Record Audio", "Upload Video","Record Video" 
+                                ,"File"], label="Input Type", value="Upload Audio")
+            
+            audio1 = gr.Audio(source="upload", type="filepath", label="Upload Audio",
+                                interactive= True, visible= True)
+            audio2 = gr.Audio(source="microphone", label="Record Audio", type="filepath",
+                                interactive= True, visible= False)
+            video1 = gr.Video(source="upload", type="filepath", label="Upload Video",
+                                interactive= True, visible= False)
+            video2 = gr.Video(source="webcam", label="Record Video", type="filepath",
+                                interactive= True, visible= False)
+            file_in = gr.File(label="Upload File", interactive= True, visible= False)
+            
+            submit = gr.Button()
+        
+        with gr.Column():
+            
+            out_txt = gr.Textbox(label="Output",
+                                    visible= True, show_copy_button=True)
+            
+            out_json = gr.JSON(label="JSON Output",
+                                visible= False, show_copy_button=True)
+            
+            annoation = gr.Textbox(label="Name your speaker's",
+                                   info= "Please provide a list of the speakers arranged \
+                                   in the order in which they appear in the input. Use comma ',' \
+                                   as a seperator. Be aware that the first name is given \
+                                    to SPEAKER_00 the second to SPEAKER_01 and so on.",
+                                   visible= False, interactive= True)
+            
+            annotate = gr.Button(value="Annotate", visible= False, interactive= True)
+        
+    # Define usage of components
+    input.change(fn=select_origin, inputs=[input],
+                    outputs=[audio1, audio2, video1, video2, file_in])
+    
+    task.change(fn=select_task, inputs=[task],
+                outputs=[num_speakers, translate, language])
+    
+    translate.change(fn= lambda x : gr.update(value = x),
+                        inputs=[translate], outputs=[translate])
+    num_speakers.change(fn= lambda x : gr.update(value = x),
+                        inputs=[num_speakers], outputs=[num_speakers])
+    language.change(fn= lambda x : gr.update(value = x), 
+                    inputs=[language], outputs=[language])
+    
+    submit.click(fn = run_scribe, 
+                    inputs=[task, num_speakers, translate, language, audio1,
+                            audio2, video1, video2, file_in],
+                    outputs=[out_txt, out_json, annoation, annotate])
+    
+    annotate.click(fn = annotate_output, inputs=[annoation, out_json],
+                    outputs=[out_txt, out_json])
+    
+
+demo.queue().launch()

scraibe/.pyannotetoken

@@ -0,0 +1 @@
+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

scraibe/app/gradio_app.py

@@ -35,7 +35,7 @@ Usage:
 import json
 
 import gradio as gr
-from autotranscript import AutoTranscribe, Transcript
+from scraibe import AutoTranscribe, Transcript
 
 
 theme = gr.themes.Soft(

scraibe/autotranscript.py

@@ -126,7 +126,6 @@ class AutoTranscribe:
         
         diarisation = self.diariser.diarization(dia_audio, **kwargs)
         
-        
         if not diarisation["segments"]:
             print("No segments found. Try to run transcription without diarisation.")
  
@@ -145,8 +144,6 @@ class AutoTranscribe:
         # Transcribe each segment and store the results
         final_transcript = dict()
         
-        
-        
         for i in trange(len(diarisation["segments"]), desc= "Transcribing"):
             
             seg = diarisation["segments"][i]

scraibe/version.py

@@ -1,69 +1,69 @@
-import os
+import os
-import subprocess as sp
+import subprocess as sp
-
+
-MAJOR = 0
+MAJOR = 0
-MINOR = 1
+MINOR = 1
-MICRO = 0
+MICRO = 0
-MICRO_POST = 0
+MICRO_POST = 0
-ISRELEASED = False
+ISRELEASED = False
-VERSION = '%d.%d.%d.%d' % (MAJOR, MINOR, MICRO, MICRO_POST)
+VERSION = '%d.%d.%d.%d' % (MAJOR, MINOR, MICRO, MICRO_POST)
-
+
-# Return the git revision as a string
+# Return the git revision as a string
-# taken from numpy/numpy
+# taken from numpy/numpy
-def git_version():
+def git_version():
-    def _minimal_ext_cmd(cmd):
+    def _minimal_ext_cmd(cmd):
-        # construct minimal environment
+        # construct minimal environment
-        env = {}
+        env = {}
-        for k in ['SYSTEMROOT', 'PATH', 'HOME']:
+        for k in ['SYSTEMROOT', 'PATH', 'HOME']:
-            v = os.environ.get(k)
+            v = os.environ.get(k)
-            if v is not None:
+            if v is not None:
-                env[k] = v
+                env[k] = v
-
+
-        # LANGUAGE is used on win32
+        # LANGUAGE is used on win32
-        env['LANGUAGE'] = 'C'
+        env['LANGUAGE'] = 'C'
-        env['LANG'] = 'C'
+        env['LANG'] = 'C'
-        env['LC_ALL'] = 'C'
+        env['LC_ALL'] = 'C'
-
+
-        out = sp.Popen(cmd, stdout=sp.PIPE, stderr=sp.PIPE, env=env).communicate()[0]
+        out = sp.Popen(cmd, stdout=sp.PIPE, stderr=sp.PIPE, env=env).communicate()[0]
-        return out
+        return out
-
+
-    try:
+    try:
-        out = _minimal_ext_cmd(['git', 'rev-parse', 'HEAD'])
+        out = _minimal_ext_cmd(['git', 'rev-parse', 'HEAD'])
-        GIT_REVISION = out.strip().decode('ascii')
+        GIT_REVISION = out.strip().decode('ascii')
-    except OSError:
+    except OSError:
-        GIT_REVISION = "Unknown"
+        GIT_REVISION = "Unknown"
-
+
-    return GIT_REVISION
+    return GIT_REVISION
-
+
-def _get_git_version():
+def _get_git_version():
-    cwd = os.getcwd()
+    cwd = os.getcwd()
-
+
-    # go to the main directory
+    # go to the main directory
-    fdir = os.path.dirname(os.path.abspath(__file__))
+    fdir = os.path.dirname(os.path.abspath(__file__))
-    maindir = os.path.abspath(os.path.join(fdir, ".."))
+    maindir = os.path.abspath(os.path.join(fdir, ".."))
-    # maindir = fdir # os.path.join(fdir, "..")
+    # maindir = fdir # os.path.join(fdir, "..")
-    os.chdir(maindir)
+    os.chdir(maindir)
-
+
-    # get git version
+    # get git version
-    res = git_version()
+    res = git_version()
-
+
-    # restore the cwd
+    # restore the cwd
-    os.chdir(cwd)
+    os.chdir(cwd)
-    return res
+    return res
-
+
-def get_version(build_version=False):
+def get_version(build_version=False):
-    if ISRELEASED:
+    if ISRELEASED:
-        return VERSION
+        return VERSION
-
+
-    # unreleased version
+    # unreleased version
-    GIT_REVISION = _get_git_version()
+    GIT_REVISION = _get_git_version()
-
+
-    if build_version:
+    if build_version:
-        import datetime as dt
+        import datetime as dt
-        date = dt.date.strftime(dt.datetime.now(), "%Y%m%d%H%M%S")
+        date = dt.date.strftime(dt.datetime.now(), "%Y%m%d%H%M%S")
-        return VERSION + ".dev" + date
+        return VERSION + ".dev" + date
-    else:
+    else:
-        return VERSION + ".dev0+" + GIT_REVISION[:7]
+        return VERSION + ".dev0+" + GIT_REVISION[:7]
-
+
-
+
-
+

setup.py

@@ -2,7 +2,7 @@ import pkg_resources
 import os
 from setuptools import setup, find_packages
 
-module_name = "autotranscript"
+module_name = "scraibe"
 github_url = "https://github.com/JSchmie/autotranscript"
 
 file_dir = os.path.dirname(os.path.realpath(__file__))
@@ -18,7 +18,7 @@ with open(verfile, "r") as fp:
 
 ############### setup ###############
 
-build_version = "AUTOTRANSCRIPT_BUILD" in os.environ
+build_version = "SCRAIBE_BUILD" in os.environ
 
 if __name__ == "__main__":
 
@@ -42,5 +42,5 @@ if __name__ == "__main__":
         description='Transcription tool for audio files based on Whisper and Pyannote',
         package_data={ "header" : ["app/header.html"], "logo" : ["app/Logo_KIDA_bmel_green.svg"]},
         entry_points={'console_scripts':
-            ['autotranscript = autotranscript.cli:cli']}
+            ['scraibe = scraibe.cli:cli']}
     )

test_autotranscript.py

@@ -1,5 +1,5 @@
 import pytest
-from autotranscript import Transcriber
+from scraibe import Transcriber
 from unittest.mock import patch, mock_open
 import os
 
@@ -55,7 +55,7 @@ def test_save_transcript_to_file(transcriber):
     
 # Test Diaraization class
 
-from autotranscript import Diariser
+from scraibe import Diariser
 
 @pytest.fixture
 def diarisation():
@@ -83,7 +83,7 @@ def test_diarisation(diarisation):
 
 # Test AudioProcessor
 
-from autotranscript import AudioProcessor , TorchAudioProcessor
+from scraibe import AudioProcessor , TorchAudioProcessor
 
 
 def test_AudioProcessor_init():

transcribe.py

@@ -18,16 +18,14 @@
 # os.environ['HF_HOME'] = os.path.expanduser("~/PycharmProjects/autotranscript/autotranscript/models")
 
 
-from autotranscript import AutoTranscribe
+from scraibe import AutoTranscribe
-
 model = AutoTranscribe()
 
-text = model.transcribe("test.mp4")
+text = model.autotranscribe('kida.mp4', num_speakers=2)
 
 print("Transcription:\n")
 print(text)
 
-
 # from autotranscript.misc import *
 # import os