This repository has been archived by the owner on Nov 29, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 45
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
fix: MP3 file test for Text-to-Speech SSML addresses [(#2378)](Google…
…CloudPlatform/python-docs-samples#2378) * fix: refactored MP3 file tests * fix: moving resources to cloud-client/resources * fix: removing expected_example.mp3
- Loading branch information
1 parent
aa66954
commit 338fa08
Showing
4 changed files
with
168 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
<speak>123 Street Ln, Small Town, IL 12345 USA | ||
<break time="2s"/>1 Jenny St & Number St, Tutone City, CA 86753 | ||
<break time="2s"/>1 Piazza del Fibonacci, 12358 Pisa, Italy | ||
<break time="2s"/></speak> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
123 Street Ln, Small Town, IL 12345 USA | ||
1 Jenny St & Number St, Tutone City, CA 86753 | ||
1 Piazza del Fibonacci, 12358 Pisa, Italy |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,112 @@ | ||
# Copyright 2019 Google LLC | ||
# | ||
# Licensed under the Apache License, Version 2.0 (the "License"); | ||
# you may not use this file except in compliance with the License. | ||
# You may obtain a copy of the License at | ||
# | ||
# http://www.apache.org/licenses/LICENSE-2.0 | ||
# | ||
# Unless required by applicable law or agreed to in writing, software | ||
# distributed under the License is distributed on an "AS IS" BASIS, | ||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
# See the License for the specific language governing permissions and | ||
# limitations under the License. | ||
|
||
|
||
# [START tts_ssml_address_imports] | ||
from google.cloud import texttospeech | ||
|
||
import html | ||
# [END tts_ssml_address_imports] | ||
|
||
|
||
# [START tts_ssml_address_audio] | ||
def ssml_to_audio(ssml_text, outfile): | ||
# Generates SSML text from plaintext. | ||
# | ||
# Given a string of SSML text and an output file name, this function | ||
# calls the Text-to-Speech API. The API returns a synthetic audio | ||
# version of the text, formatted according to the SSML commands. This | ||
# function saves the synthetic audio to the designated output file. | ||
# | ||
# Args: | ||
# ssml_text: string of SSML text | ||
# outfile: string name of file under which to save audio output | ||
# | ||
# Returns: | ||
# nothing | ||
|
||
# Instantiates a client | ||
client = texttospeech.TextToSpeechClient() | ||
|
||
# Sets the text input to be synthesized | ||
synthesis_input = texttospeech.types.SynthesisInput(ssml=ssml_text) | ||
|
||
# Builds the voice request, selects the language code ("en-US") and | ||
# the SSML voice gender ("MALE") | ||
voice = texttospeech.types.VoiceSelectionParams( | ||
language_code='en-US', | ||
ssml_gender=texttospeech.enums.SsmlVoiceGender.MALE) | ||
|
||
# Selects the type of audio file to return | ||
audio_config = texttospeech.types.AudioConfig( | ||
audio_encoding=texttospeech.enums.AudioEncoding.MP3) | ||
|
||
# Performs the text-to-speech request on the text input with the selected | ||
# voice parameters and audio file type | ||
response = client.synthesize_speech(synthesis_input, voice, audio_config) | ||
|
||
# Writes the synthetic audio to the output file. | ||
with open(outfile, 'wb') as out: | ||
out.write(response.audio_content) | ||
print('Audio content written to file ' + outfile) | ||
# [END tts_ssml_address_audio] | ||
|
||
|
||
# [START tts_ssml_address_ssml] | ||
def text_to_ssml(inputfile): | ||
# Generates SSML text from plaintext. | ||
# Given an input filename, this function converts the contents of the text | ||
# file into a string of formatted SSML text. This function formats the SSML | ||
# string so that, when synthesized, the synthetic audio will pause for two | ||
# seconds between each line of the text file. This function also handles | ||
# special text characters which might interfere with SSML commands. | ||
# | ||
# Args: | ||
# inputfile: string name of plaintext file | ||
# | ||
# Returns: | ||
# A string of SSML text based on plaintext input | ||
|
||
# Parses lines of input file | ||
with open(inputfile, 'r') as f: | ||
raw_lines = f.read() | ||
|
||
# Replace special characters with HTML Ampersand Character Codes | ||
# These Codes prevent the API from confusing text with | ||
# SSML commands | ||
# For example, '<' --> '<' and '&' --> '&' | ||
|
||
escaped_lines = html.escape(raw_lines) | ||
|
||
# Convert plaintext to SSML | ||
# Wait two seconds between each address | ||
ssml = '<speak>{}</speak>'.format( | ||
escaped_lines.replace('\n', '\n<break time="2s"/>')) | ||
|
||
# Return the concatenated string of ssml script | ||
return ssml | ||
# [END tts_ssml_address_ssml] | ||
|
||
|
||
# [START tts_ssml_address_test] | ||
def main(): | ||
# test example address file | ||
plaintext = 'resources/example.txt' | ||
ssml_text = text_to_ssml(plaintext) | ||
ssml_to_audio(ssml_text, 'resources/example.mp3') | ||
# [END tts_ssml_address_test] | ||
|
||
|
||
if __name__ == '__main__': | ||
main() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,49 @@ | ||
# Copyright 2019 Google LLC | ||
# | ||
# Licensed under the Apache License, Version 2.0 (the "License"); | ||
# you may not use this file except in compliance with the License. | ||
# You may obtain a copy of the License at | ||
# | ||
# http://www.apache.org/licenses/LICENSE-2.0 | ||
# | ||
# Unless required by applicable law or agreed to in writing, software | ||
# distributed under the License is distributed on an "AS IS" BASIS, | ||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
# See the License for the specific language governing permissions and | ||
# limitations under the License. | ||
|
||
from ssml_addresses import text_to_ssml | ||
from ssml_addresses import ssml_to_audio | ||
|
||
import filecmp | ||
import os | ||
|
||
|
||
def test_text_to_ssml(capsys): | ||
|
||
# Read expected SSML output from resources | ||
with open('resources/example.ssml', 'r') as f: | ||
expected_ssml = f.read() | ||
|
||
# Assert plaintext converted to SSML | ||
input_text = 'resources/example.txt' | ||
tested_ssml = text_to_ssml(input_text) | ||
assert expected_ssml == tested_ssml | ||
|
||
|
||
def test_ssml_to_audio(capsys): | ||
|
||
# Read SSML input from resources | ||
with open('resources/example.ssml', 'r') as f: | ||
input_ssml = f.read() | ||
|
||
# Assert audio file generated | ||
ssml_to_audio(input_ssml, 'test_example.mp3') | ||
out, err = capsys.readouterr() | ||
|
||
# Assert MP3 file created | ||
assert os.path.isfile('test_example.mp3') | ||
assert "Audio content written to file test_example.mp3" in out | ||
|
||
# Delete MP3 test file | ||
os.remove("test_example.mp3") |