Python based interface for interacting with Google Cloud's Speech-to-Text API and Cloud Storage API.
Project description
TranscribeInterviews
Python interface for interacting with the Google Speech-to-Text API and Google Cloud Storage API for the purposes of automatic audio transcription. Usage requires a google cloud account with a credential's file issued from it with permissions for both APIs.
Installation
pip install InterviewTranscriber
Example End-to-End Workflow
# 1) Upload audio file(s) to Google Coud Coldline Storage bucket.
from Transcriber.Google.Storage import Storage
from Transcriber.Google.Transcriber import TranscriberBeta
storage_connection = Storage(project_id='<project_id>',
credential_path='<path_to_credential_file')
storage_connection.upload_file(bucket_name='<cloud_bucket_name>',
source_file_path='<path_to_source_file>')
# 2) Get URI list of files in bucket
file_list = storage_connection.get_uris(bucket_name='<cloud_bucket_name>')
# 3) Send API call to transcribe audio
transcriber = TranscriberBeta(output_directory='<path_to_output_directory>',
credential_path='<path_to_credential_file>',
contexts_path='<path_to_contexts_file.txt>',
speaker_count=2,
diarization=True)
transcriber.get_transcriptions(uris=file_list)
# 4) Export as a Praat TextGrid
transcriber.export_textgrids()
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for InterviewTranscriber-0.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8ad612adb4bdd18e7398c4fe9db618ccc94c6e0dac2f5e712bce498f3b964935 |
|
MD5 | 33d22fe694861e38d6631cf687b45e0c |
|
BLAKE2b-256 | 07fcc054ec8275e020724da40b690f3e56c21560cf9eaa43817802eda2bc4b82 |
Close
Hashes for InterviewTranscriber-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0de7071b8a0efe48922cfa89ab11257d6d35a3c1ba6452fbbd84e338093ac683 |
|
MD5 | 13c29d3842646e49373304d5e5b1425e |
|
BLAKE2b-256 | 0beaac60f07b1fbf9219e0e691763f39bc077b2324be3658dae11e7a8b401d42 |