Spracherkennung mit Transformers in Python

Automatische Spracherkennung (ASR) ist die Technologie, mit der wir menschliche Sprache in digitalen Text umwandeln können. Dieses Tutorial wird in das aktuelle State-of-the-Art-Modell namens Wav2vec2 unter Verwendung der Huggingface-Transformer-Bibliothek in Python eintauchen.

Wav2Vec2  ist ein vortrainiertes Modell, das nur mit Sprachaudio (selbstüberwacht) trainiert wurde, gefolgt von einer Feinabstimmung mit transkribierten Sprachdaten ( LibriSpeech - Datensatz). Es hat frühere halbüberwachte Modelle übertroffen.

Wie beim Masked Language Modeling codiert Wav2Vec2 Sprachaudio über ein mehrschichtiges neuronales Faltungsnetz und maskiert dann Spannen der resultierenden latenten Sprachdarstellungen. Diese Repräsentationen werden dann in ein Transformer-Netzwerk eingespeist, um kontextualisierte Repräsentationen zu erstellen; Weitere Informationen finden Sie im Wav2Vec2 -Papier .

Lassen Sie uns zunächst die erforderlichen Bibliotheken installieren:

$ pip3 install transformers==4.11.2 soundfile sentencepiece torchaudio pydub pyaudio

Wir verwenden Torchaudio zum Laden von Audiodateien. Beachten Sie, dass Sie PyAudio installieren müssen, wenn Sie den Code in Ihrer Umgebung verwenden möchten, und PyDub, wenn Sie sich in einer Colab-Umgebung befinden. Wir werden sie für die Aufnahme vom Mikrofon in Python verwenden.

Einstieg

Lassen Sie uns unsere Bibliotheken importieren:

from transformers import *
import torch
import soundfile as sf
# import librosa
import os
import torchaudio

Laden Sie als Nächstes den Prozessor und die Modellgewichte von wav2vec2:

# model_name = "facebook/wav2vec2-base-960h" # 360MB
model_name = "facebook/wav2vec2-large-960h-lv60-self" # 1.18GB

processor = Wav2Vec2Processor.from_pretrained(model_name)
model = Wav2Vec2ForCTC.from_pretrained(model_name)

Es gibt zwei am häufigsten verwendete Modellarchitekturen und Gewichtungen für wav2vec. wav2vec2-base-960hist eine Basisarchitektur mit einer Größe von etwa 360 MB, erreichte eine Wortfehlerrate (WER) von 3,4 % auf dem sauberen Testsatz und wurde mit 960 Stunden LibriSpeech-Datensatz auf 16-kHz-abgetastetem Sprachaudio trainiert.

Auf der anderen Seite wav2vec2-large-960h-lv60-selfist ein größeres Modell mit etwa 1,18 GB groß (passt wahrscheinlich nicht in Ihren Laptop-RAM), erzielte aber 1,9 % WER (je niedriger, desto besser) auf dem sauberen Testsatz. Dieser ist also viel besser für die Erkennung, aber schwerer und braucht mehr Zeit für die Schlussfolgerung. Wählen Sie frei aus, welches am besten zu Ihnen passt.

Wav2Vec2 wurde mit Connectionist Temporal Classification (CTC) trainiert , deshalb verwenden wir die Wav2Vec2ForCTCKlasse zum Laden des Modells.

Als nächstes sind hier einige Audiobeispiele:

# audio_url = "https://github.com/x4nth055/pythoncode-tutorials/raw/master/machine-learning/speech-recognition/16-122828-0002.wav"
audio_url = "https://github.com/x4nth055/pythoncode-tutorials/raw/master/machine-learning/speech-recognition/30-4447-0004.wav"
# audio_url = "https://github.com/x4nth055/pythoncode-tutorials/raw/master/machine-learning/speech-recognition/7601-291468-0006.wav"

Vorbereiten der Audiodatei

Fühlen Sie sich frei, eine der oben genannten Audiodateien auszuwählen. Die untere Zelle lädt die Audiodatei:

# load our wav file
speech, sr = torchaudio.load(audio_url)
speech = speech.squeeze()
# or using librosa
# speech, sr = librosa.load(audio_file, sr=16000)
sr, speech.shape
(16000, torch.Size([274000]))

Die torchaudio.load()Funktion lädt die Audiodatei und gibt das Audio als Vektor und die Abtastrate zurück. Es lädt die Datei auch automatisch herunter, wenn es sich um eine URL handelt. Wenn es sich um einen Pfad auf der Festplatte handelt, wird er auch geladen.

Beachten Sie, dass wir die squeeze()Methode auch verwenden, um die Dimensionen mit der Größe 1 zu entfernen, dh den Tensor von (1, 274000)in umzuwandeln (274000,).

Als Nächstes müssen wir sicherstellen, dass die Eingangsaudiodatei für das Modell die Abtastrate von 16000 Hz hat, da wav2vec2 darauf trainiert wird:

# resample from whatever the audio sampling rate to 16000
resampler = torchaudio.transforms.Resample(sr, 16000)
speech = resampler(speech)
speech.shape
torch.Size([274000])

Wir haben Resamplevon Torchaudio.transforms verwendet , was uns hilft, die geladene Audiodatei im Handumdrehen von einer Abtastrate in eine andere zu konvertieren.

Bevor wir die Schlussfolgerung ziehen, übergeben wir den Audiovektor an den wav2vec2-Prozessor:

# tokenize our wav
input_values = processor(speech, return_tensors="pt", sampling_rate=16000)["input_values"]
input_values.shape
torch.Size([1, 274000])

Wir geben das Argument sampling_rateand pass "pt"to return_tensorsan, um PyTorch-Tensoren in den Ergebnissen zu erhalten.

Inferenz durchführen

Lassen Sie uns nun den Vektor in unser Modell übergeben:

# perform inference
logits = model(input_values)["logits"]
logits.shape
torch.Size([1, 856, 32])

Übergeben der Logits an torch.argmax(), um die wahrscheinliche Vorhersage zu erhalten:

# use argmax to get the predicted IDs
predicted_ids = torch.argmax(logits, dim=-1)
predicted_ids.shape
torch.Size([1, 856, 32])

Wenn wir sie zurück in Text dekodieren, senken wir auch den Text, da er in Großbuchstaben steht:

# decode the IDs to text
transcription = processor.decode(predicted_ids[0])
transcription.lower()
and missus goddard three ladies almost always at the service of an invitation from hartfield and who were fetched and carried home so often that mister woodhouse thought it no hardship for either james or the horses had it taken place only once a year it would have been a grievance

Den Kodex zusammenfassen

Lassen Sie uns nun unseren gesamten vorherigen Code in einer einzigen Funktion zusammenfassen, die den Audiopfad akzeptiert und die Transkription zurückgibt:

def get_transcription(audio_path):
  # load our wav file
  speech, sr = torchaudio.load(audio_path)
  speech = speech.squeeze()
  # or using librosa
  # speech, sr = librosa.load(audio_file, sr=16000)
  # resample from whatever the audio sampling rate to 16000
  resampler = torchaudio.transforms.Resample(sr, 16000)
  speech = resampler(speech)
  # tokenize our wav
  input_values = processor(speech, return_tensors="pt", sampling_rate=16000)["input_values"]
  # perform inference
  logits = model(input_values)["logits"]
  # use argmax to get the predicted IDs
  predicted_ids = torch.argmax(logits, dim=-1)
  # decode the IDs to text
  transcription = processor.decode(predicted_ids[0])
  return transcription.lower()

Großartig, Sie können jeden Audio-Sprachdateipfad übergeben:

get_transcription("http://www0.cs.ucl.ac.uk/teaching/GZ05/samples/lathe.wav")
a late is a big tool grab every dish of sugar

Großartig, jetzt, wenn Sie Ihre Stimme verwenden möchten!

What is GEEK

Buddha Community

Ray  Patel

Ray Patel

1619510796

Lambda, Map, Filter functions in python

Welcome to my Blog, In this article, we will learn python lambda function, Map function, and filter function.

Lambda function in python: Lambda is a one line anonymous function and lambda takes any number of arguments but can only have one expression and python lambda syntax is

Syntax: x = lambda arguments : expression

Now i will show you some python lambda function examples:

#python #anonymous function python #filter function in python #lambda #lambda python 3 #map python #python filter #python filter lambda #python lambda #python lambda examples #python map

Shardul Bhatt

Shardul Bhatt

1626775355

Why use Python for Software Development

No programming language is pretty much as diverse as Python. It enables building cutting edge applications effortlessly. Developers are as yet investigating the full capability of end-to-end Python development services in various areas. 

By areas, we mean FinTech, HealthTech, InsureTech, Cybersecurity, and that's just the beginning. These are New Economy areas, and Python has the ability to serve every one of them. The vast majority of them require massive computational abilities. Python's code is dynamic and powerful - equipped for taking care of the heavy traffic and substantial algorithmic capacities. 

Programming advancement is multidimensional today. Endeavor programming requires an intelligent application with AI and ML capacities. Shopper based applications require information examination to convey a superior client experience. Netflix, Trello, and Amazon are genuine instances of such applications. Python assists with building them effortlessly. 

5 Reasons to Utilize Python for Programming Web Apps 

Python can do such numerous things that developers can't discover enough reasons to admire it. Python application development isn't restricted to web and enterprise applications. It is exceptionally adaptable and superb for a wide range of uses.

Robust frameworks 

Python is known for its tools and frameworks. There's a structure for everything. Django is helpful for building web applications, venture applications, logical applications, and mathematical processing. Flask is another web improvement framework with no conditions. 

Web2Py, CherryPy, and Falcon offer incredible capabilities to customize Python development services. A large portion of them are open-source frameworks that allow quick turn of events. 

Simple to read and compose 

Python has an improved sentence structure - one that is like the English language. New engineers for Python can undoubtedly understand where they stand in the development process. The simplicity of composing allows quick application building. 

The motivation behind building Python, as said by its maker Guido Van Rossum, was to empower even beginner engineers to comprehend the programming language. The simple coding likewise permits developers to roll out speedy improvements without getting confused by pointless subtleties. 

Utilized by the best 

Alright - Python isn't simply one more programming language. It should have something, which is the reason the business giants use it. Furthermore, that too for different purposes. Developers at Google use Python to assemble framework organization systems, parallel information pusher, code audit, testing and QA, and substantially more. Netflix utilizes Python web development services for its recommendation algorithm and media player. 

Massive community support 

Python has a steadily developing community that offers enormous help. From amateurs to specialists, there's everybody. There are a lot of instructional exercises, documentation, and guides accessible for Python web development solutions. 

Today, numerous universities start with Python, adding to the quantity of individuals in the community. Frequently, Python designers team up on various tasks and help each other with algorithmic, utilitarian, and application critical thinking. 

Progressive applications 

Python is the greatest supporter of data science, Machine Learning, and Artificial Intelligence at any enterprise software development company. Its utilization cases in cutting edge applications are the most compelling motivation for its prosperity. Python is the second most well known tool after R for data analytics.

The simplicity of getting sorted out, overseeing, and visualizing information through unique libraries makes it ideal for data based applications. TensorFlow for neural networks and OpenCV for computer vision are two of Python's most well known use cases for Machine learning applications.

Summary

Thinking about the advances in programming and innovation, Python is a YES for an assorted scope of utilizations. Game development, web application development services, GUI advancement, ML and AI improvement, Enterprise and customer applications - every one of them uses Python to its full potential. 

The disadvantages of Python web improvement arrangements are regularly disregarded by developers and organizations because of the advantages it gives. They focus on quality over speed and performance over blunders. That is the reason it's a good idea to utilize Python for building the applications of the future.

#python development services #python development company #python app development #python development #python in web development #python software development

Art  Lind

Art Lind

1602968400

Python Tricks Every Developer Should Know

Python is awesome, it’s one of the easiest languages with simple and intuitive syntax but wait, have you ever thought that there might ways to write your python code simpler?

In this tutorial, you’re going to learn a variety of Python tricks that you can use to write your Python code in a more readable and efficient way like a pro.

Let’s get started

Swapping value in Python

Instead of creating a temporary variable to hold the value of the one while swapping, you can do this instead

>>> FirstName = "kalebu"
>>> LastName = "Jordan"
>>> FirstName, LastName = LastName, FirstName 
>>> print(FirstName, LastName)
('Jordan', 'kalebu')

#python #python-programming #python3 #python-tutorials #learn-python #python-tips #python-skills #python-development

Art  Lind

Art Lind

1602666000

How to Remove all Duplicate Files on your Drive via Python

Today you’re going to learn how to use Python programming in a way that can ultimately save a lot of space on your drive by removing all the duplicates.

Intro

In many situations you may find yourself having duplicates files on your disk and but when it comes to tracking and checking them manually it can tedious.

Heres a solution

Instead of tracking throughout your disk to see if there is a duplicate, you can automate the process using coding, by writing a program to recursively track through the disk and remove all the found duplicates and that’s what this article is about.

But How do we do it?

If we were to read the whole file and then compare it to the rest of the files recursively through the given directory it will take a very long time, then how do we do it?

The answer is hashing, with hashing can generate a given string of letters and numbers which act as the identity of a given file and if we find any other file with the same identity we gonna delete it.

There’s a variety of hashing algorithms out there such as

  • md5
  • sha1
  • sha224, sha256, sha384 and sha512

#python-programming #python-tutorials #learn-python #python-project #python3 #python #python-skills #python-tips

How To Compare Tesla and Ford Company By Using Magic Methods in Python

Magic Methods are the special methods which gives us the ability to access built in syntactical features such as ‘<’, ‘>’, ‘==’, ‘+’ etc…

You must have worked with such methods without knowing them to be as magic methods. Magic methods can be identified with their names which start with __ and ends with __ like init, call, str etc. These methods are also called Dunder Methods, because of their name starting and ending with Double Underscore (Dunder).

Now there are a number of such special methods, which you might have come across too, in Python. We will just be taking an example of a few of them to understand how they work and how we can use them.

1. init

class AnyClass:
    def __init__():
        print("Init called on its own")
obj = AnyClass()

The first example is _init, _and as the name suggests, it is used for initializing objects. Init method is called on its own, ie. whenever an object is created for the class, the init method is called on its own.

The output of the above code will be given below. Note how we did not call the init method and it got invoked as we created an object for class AnyClass.

Init called on its own

2. add

Let’s move to some other example, add gives us the ability to access the built in syntax feature of the character +. Let’s see how,

class AnyClass:
    def __init__(self, var):
        self.some_var = var
    def __add__(self, other_obj):
        print("Calling the add method")
        return self.some_var + other_obj.some_var
obj1 = AnyClass(5)
obj2 = AnyClass(6)
obj1 + obj2

#python3 #python #python-programming #python-web-development #python-tutorials #python-top-story #python-tips #learn-python