type

project_id

private_key_id

private_key

client_email

client_id

auth_uri

token_uri

auth_provider_x509_cert_url

client_x509_cert_url

unique_bucket_name

Lead the GenAI revolution by incorporating Google’s Speech-to-Text AI in Python. Learn use cases, execute demos, master recognition configuration, and improve transcription accuracy. Future-proof your skills.

mysdk.tar.gz

transcription demo code

key storing

lady susan - copy audio

Punctuation 

Multi language

Multi audio

Diarization

Diarization-copy

Speech adaptation phrases

Speech adaptation classes

Speech adaptation boost

Speech adaptation boost-tuning

Recognition model

Enhanced model

More than one minute

Welcome! My name is Bruce Bookman and I’m a subject matter expert in Conversational AI at Google. In this course, I will show you how to incorporate Google’s powerful Speech-to-Text Artificial Intelligence models into a Python program.
Google Speech-to-Text enables you to convert audio to text by applying neural network models in an easy-to-use API. So, in this course, you will start by understanding the main use cases for Speech-to-Text (STT) and an overview of the API.
You will then execute some demo code for the API to create a transcription for an audio file. Don’t worry, you’ll run through each line of code to make sure you’ve got it down.
In the following chapters, you will focus on recognition configuration, speech adaptation, and the different models used for speech recognition. Lastly, you will learn about word error rate and how to measure transcription accuracy.
By the end of this course, you will be able to inject STT in your own Python projects and you will have a great new skill for your resume.

Google Cloud: AI Speech-to-Text with Python 3

## Imports
```python
## [START speech_quickstart_beta]
from google.cloud import speech_v1p1beta1
from google.cloud.speech_v1p1beta1 import enums
```

The first line allows access to the speech API client,
The second line brings in ```enums``` that are useful later in the code, such as ```enums.RecognitionConfig.AudioEncoding.MP3```.
 

## Client

The function `sample_recognize` starts by creating a client that will be the main actor and that will make the calls to the API.

This will be a common pattern for any function that leverages the API.

```python
def sample_recognize(storage_uri):
    ...
    client = speech_v1p1beta1.SpeechClient()
    ...
```

## Variables
The code defaults to transcribing a specific audio file.  This file is known to have specific attributes, such as the encoding and language.

* Synchronous Speech Recognition Requests require:

|  **Fields** | **Description**  |
| - | - |
| ```encoding```  | Specifies the encoding scheme of the supplied audio (of type AudioEncoding). The [encoding](https://cloud.google.com/speech-to-text/docs/encoding#audio-encodings) field is optional for FLAC and WAV files.  |
|  ```sample_rate_hertz```  |  Specifies the sample rate (in Hertz) of the supplied audio. The sampleRateHertz field is optional for FLAC and WAV files. |
|  ```language_code``` |  Contains the language + region/locale to use for speech recognition of the supplied audio. The language code must be a [BCP-47 identifier](https://cloud.google.com/speech-to-text/docs/languages). |

# Imports
```python
## [START speech_quickstart_beta]
from google.cloud import speech_v1p1beta1
from google.cloud.speech_v1p1beta1 import enums
```

The first line allows access to the speech API client,
The second line brings in ```enums``` that are useful later in the code, such as ```enums.RecognitionConfig.AudioEncoding.MP3```.
 

# Client

The function `sample_recognize` starts by creating a client that will be the main actor and that will make the calls to the API.

This will be a common pattern for any function that leverages the API.

```python
def sample_recognize(storage_uri):
    ...
    client = speech_v1p1beta1.SpeechClient()
    ...
```

# Variables
The code defaults to transcribing a specific audio file.  This file is known to have specific attributes, such as the encoding and language.

* Synchronous Speech Recognition Requests require:

|  **Fields** | **Description**  |
| - | - |
| ```encoding```  | Specifies the encoding scheme of the supplied audio (of type AudioEncoding). The [encoding](https://cloud.google.com/speech-to-text/docs/encoding#audio-encodings) field is optional for FLAC and WAV files.  |
|  ```sample_rate_hertz```  |  Specifies the sample rate (in Hertz) of the supplied audio. The sampleRateHertz field is optional for FLAC and WAV files. |
|  ```language_code``` |  Contains the language + region/locale to use for speech recognition of the supplied audio. The language code must be a [BCP-47 identifier](https://cloud.google.com/speech-to-text/docs/languages). |

Here, we pull apart the demo code to understand how to access the API and the results.


Fields	Description
`encoding`	Specifies the encoding scheme of the supplied audio (of type AudioEncoding). The encoding field is optional for FLAC and WAV files.
`sample_rate_hertz`	Specifies the sample rate (in Hertz) of the supplied audio. The sampleRateHertz field is optional for FLAC and WAV files.
`language_code`	Contains the language + region/locale to use for speech recognition of the supplied audio. The language code

Getting Started

Your First Program

Recognition Configuration

Speech Adaptation

Models

Word Error Rate WER

Final Thoughts

Appendix

Demo Code Deep Dive

Imports

Client

Variables