https://github.com/wakame1367/gcp_speech2text

https://github.com/wakame1367/gcp_speech2text

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/wakame1367/gcp_speech2text
• Owner: wakame1367
• License: mit
• Created: 2019-08-19T06:11:37.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2022-12-08T06:08:27.000Z (about 2 years ago)
• Last Synced: 2023-03-10T20:56:55.994Z (almost 2 years ago)
• Language: Python
• Size: 39.1 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# gcp_speech2text

This repository is **GCP Speech2Text API Python Sample**

## Before you start

**Setup Project** and **export GOOGLE_APPLICATION_CREDENTIALS**, **Install Cloud SDK**

[Cloud Speech-to-Text API - QuickStart](https://cloud.google.com/speech-to-text/docs/quickstart-client-libraries)

## Installing

Use [Github - pipenv](https://github.com/pypa/pipenv)

```

git clone https://github.com/wakamezake/gcp_speech2text.git

pipenv install

```

## How to use

```

python cli.py  path/to/file or gcs://path/to/file

```

```

usage: cli.py [-h] [--audio_encoding AUDIO_ENCODING] [--hertz HERTZ]

              [--language_code LANGUAGE_CODE]

              path

positional arguments:

  path                  gcs link or local file path

optional arguments:

  -h, --help            show this help message and exit

  --audio_encoding AUDIO_ENCODING

                        audio encoding format support audio encoding format:

                        https://cloud.google.com/speech-to-text/docs/encoding

                        (default=FLAC)

  --hertz HERTZ         sampling rate (default=44100)

  --language_code LANGUAGE_CODE

                        want to transcript language code support

                        language_code: https://cloud.google.com/speech-to-

                        text/docs/languages (default=en-US)

```