commit 476c07c855b4b146e66cd2f7916d3411307bc348 Author: Aleksey Filippov Date: Thu Jan 13 20:23:35 2022 +0400 Initial commit diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..cf6b82b --- /dev/null +++ b/.gitignore @@ -0,0 +1,254 @@ + +# Created by https://www.toptal.com/developers/gitignore/api/python,pycharm+all +# Edit at https://www.toptal.com/developers/gitignore?templates=python,pycharm+all + +### PyCharm+all ### +# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider +# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 + +# User-specific stuff +.idea/**/workspace.xml +.idea/**/tasks.xml +.idea/**/usage.statistics.xml +.idea/**/dictionaries +.idea/**/shelf + +# AWS User-specific +.idea/**/aws.xml + +# Generated files +.idea/**/contentModel.xml + +# Sensitive or high-churn files +.idea/**/dataSources/ +.idea/**/dataSources.ids +.idea/**/dataSources.local.xml +.idea/**/sqlDataSources.xml +.idea/**/dynamic.xml +.idea/**/uiDesigner.xml +.idea/**/dbnavigator.xml + +# Gradle +.idea/**/gradle.xml +.idea/**/libraries + +# Gradle and Maven with auto-import +# When using Gradle or Maven with auto-import, you should exclude module files, +# since they will be recreated, and may cause churn. Uncomment if using +# auto-import. +# .idea/artifacts +# .idea/compiler.xml +# .idea/jarRepositories.xml +# .idea/modules.xml +# .idea/*.iml +# .idea/modules +# *.iml +# *.ipr + +# CMake +cmake-build-*/ + +# Mongo Explorer plugin +.idea/**/mongoSettings.xml + +# File-based project format +*.iws + +# IntelliJ +out/ + +# mpeltonen/sbt-idea plugin +.idea_modules/ + +# JIRA plugin +atlassian-ide-plugin.xml + +# Cursive Clojure plugin +.idea/replstate.xml + +# SonarLint plugin +.idea/sonarlint/ + +# Crashlytics plugin (for Android Studio and IntelliJ) +com_crashlytics_export_strings.xml +crashlytics.properties +crashlytics-build.properties +fabric.properties + +# Editor-based Rest Client +.idea/httpRequests + +# Android studio 3.1+ serialized cache file +.idea/caches/build_file_checksums.ser + +### PyCharm+all Patch ### +# Ignores the whole .idea folder and all .iml files +# See https://github.com/joeblau/gitignore.io/issues/186 and https://github.com/joeblau/gitignore.io/issues/360 + +.idea/* + +# Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023 + +*.iml +modules.xml +.idea/misc.xml +*.ipr + +# Sonarlint plugin +.idea/sonarlint + +### Python ### +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +#poetry.lock + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintainted in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +#.idea/ + +# End of https://www.toptal.com/developers/gitignore/api/python,pycharm+all \ No newline at end of file diff --git a/1.wav b/1.wav new file mode 100644 index 0000000..15326bd Binary files /dev/null and b/1.wav differ diff --git a/main.py b/main.py new file mode 100644 index 0000000..c73498a --- /dev/null +++ b/main.py @@ -0,0 +1,60 @@ +#!/usr/bin/env python3 + +import json +import struct +import sys +import wave +from io import BytesIO +from urllib.request import Request, urlopen + +from scipy.io import wavfile +from scipy.io.wavfile import read as read_wav + + +def stt(wav_file: str, url: str) -> str: + print('Connecting to \'{}\'...'.format(url)) + request = Request('{}/stt'.format(url), data=_load_wav(wav_file), headers={'Content-Type': 'audio/wav'}) + result = json.loads(urlopen(request).read().decode('utf-8')) + + if not ('code' in result and 'text' in result): + raise RuntimeError('Wrong reply from server: {}'.format(result)) + return result['text'] if not result['code'] else 'Server error: [{code}]: {text}'.format(**result) + + +def _load_wav(wav_file, convert_rate=16000, convert_width=2, channels=1): + _check_wav(wav_file) + with wave.open(wav_file, 'rb') as in_: + src_data = in_.readframes(in_.getnframes()) + with BytesIO() as file: + with wave.open(file, 'wb') as out: + out.setframerate(convert_rate) + out.setsampwidth(convert_width) + out.setnchannels(channels) + out.writeframes(src_data) + result = file.getvalue() + return result + + +def _check_wav(wav_file): + sample_rate, sig = wavfile.read(wav_file) + channels = len(sig.shape) + bits = sig.dtype.base.name + if sample_rate != 16000: + raise Exception(f'Sample rate is not 16000: {sample_rate}') + if channels != 1: + raise Exception(f'Number of Channels is not 1 (Not mono): {channels}') + if bits != 'int16': + raise Exception(f'Bits per sample 16: {bits}') + + +def _main(): + if len(sys.argv) < 2: + print('Usage: {} FILE [URL]'.format(sys.argv[0])) + exit(1) + file = sys.argv[1] + server = 'http://127.0.0.1:8086' if len(sys.argv) < 3 else sys.argv[2] + print('Result: {}'.format(stt(file, server))) + + +if __name__ == '__main__': + _main() \ No newline at end of file diff --git a/test.wav b/test.wav new file mode 100644 index 0000000..694b849 Binary files /dev/null and b/test.wav differ diff --git a/untitled.wav b/untitled.wav new file mode 100644 index 0000000..f0e45a4 Binary files /dev/null and b/untitled.wav differ