Merge pull request #5 from CLARIN-PL/feature/add_base_asr_service

Add base ASR serice

poetry.lock

@@ -73,7 +73,7 @@ unicode_backport = ["unicodedata2"]
 name = "click"
 version = "8.0.1"
 description = "Composable command line interface toolkit"
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=3.6"
 
@@ -84,7 +84,7 @@ colorama = {version = "*", markers = "platform_system == \"Windows\""}
 name = "colorama"
 version = "0.4.4"
 description = "Cross-platform colored terminal text."
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 
@@ -100,6 +100,24 @@ python-versions = "*"
 numpy = "*"
 pybind11 = ">=2.2"
 
+[[package]]
+name = "flask"
+version = "2.0.1"
+description = "A simple framework for building complex web applications."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+click = ">=7.1.2"
+itsdangerous = ">=2.0"
+Jinja2 = ">=3.0"
+Werkzeug = ">=2.0"
+
+[package.extras]
+async = ["asgiref (>=3.2)"]
+dotenv = ["python-dotenv"]
+
 [[package]]
 name = "idna"
 version = "3.2"
@@ -122,6 +140,36 @@ requirements_deprecated_finder = ["pipreqs", "pip-api"]
 colors = ["colorama (>=0.4.3,<0.5.0)"]
 plugins = ["setuptools"]
 
+[[package]]
+name = "itsdangerous"
+version = "2.0.1"
+description = "Safely pass data to untrusted environments and back."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "jinja2"
+version = "3.0.1"
+description = "A very fast and expressive template engine."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+MarkupSafe = ">=2.0"
+
+[package.extras]
+i18n = ["Babel (>=2.7)"]
+
+[[package]]
+name = "markupsafe"
+version = "2.0.1"
+description = "Safely add untrusted strings to HTML/XML markup."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
 [[package]]
 name = "more-itertools"
 version = "8.8.0"
@@ -409,13 +457,24 @@ category = "dev"
 optional = false
 python-versions = "*"
 
+[[package]]
+name = "werkzeug"
+version = "2.0.1"
+description = "The comprehensive WSGI web application library."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.extras]
+watchdog = ["watchdog"]
+
 [extras]
 developer = []
 
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.8"
-content-hash = "78c43ede773a3caa4d3c131a3faf75975279c5d38ba6c9fe15b3653515e475ce"
+content-hash = "339f3a61fd3a6005117dded8ba0727e8eab938a43ad3c1b492db4ac55b8b9009"
 
 [metadata.files]
 appdirs = [
@@ -452,6 +511,10 @@ colorama = [
 fasttext = [
     {file = "fasttext-0.9.2.tar.gz", hash = "sha256:665556f1f6dcb4fcbe25fa8ebcd4f71b18fa96a090de09d88d97a60cbd29dcb5"},
 ]
+flask = [
+    {file = "Flask-2.0.1-py3-none-any.whl", hash = "sha256:a6209ca15eb63fc9385f38e452704113d679511d9574d09b2cf9183ae7d20dc9"},
+    {file = "Flask-2.0.1.tar.gz", hash = "sha256:1c4c257b1892aec1398784c63791cbaa43062f1f7aeb555c4da961b20ee68f55"},
+]
 idna = [
     {file = "idna-3.2-py3-none-any.whl", hash = "sha256:14475042e284991034cb48e06f6851428fb14c4dc953acd9be9a5e95c7b6dd7a"},
     {file = "idna-3.2.tar.gz", hash = "sha256:467fbad99067910785144ce333826c71fb0e63a425657295239737f7ecd125f3"},
@@ -460,6 +523,50 @@ isort = [
     {file = "isort-5.9.3-py3-none-any.whl", hash = "sha256:e17d6e2b81095c9db0a03a8025a957f334d6ea30b26f9ec70805411e5c7c81f2"},
     {file = "isort-5.9.3.tar.gz", hash = "sha256:9c2ea1e62d871267b78307fe511c0838ba0da28698c5732d54e2790bf3ba9899"},
 ]
+itsdangerous = [
+    {file = "itsdangerous-2.0.1-py3-none-any.whl", hash = "sha256:5174094b9637652bdb841a3029700391451bd092ba3db90600dea710ba28e97c"},
+    {file = "itsdangerous-2.0.1.tar.gz", hash = "sha256:9e724d68fc22902a1435351f84c3fb8623f303fffcc566a4cb952df8c572cff0"},
+]
+jinja2 = [
+    {file = "Jinja2-3.0.1-py3-none-any.whl", hash = "sha256:1f06f2da51e7b56b8f238affdd6b4e2c61e39598a378cc49345bc1bd42a978a4"},
+    {file = "Jinja2-3.0.1.tar.gz", hash = "sha256:703f484b47a6af502e743c9122595cc812b0271f661722403114f71a79d0f5a4"},
+]
+markupsafe = [
+    {file = "MarkupSafe-2.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:f9081981fe268bd86831e5c75f7de206ef275defcb82bc70740ae6dc507aee51"},
+    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:0955295dd5eec6cb6cc2fe1698f4c6d84af2e92de33fbcac4111913cd100a6ff"},
+    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:0446679737af14f45767963a1a9ef7620189912317d095f2d9ffa183a4d25d2b"},
+    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux2010_i686.whl", hash = "sha256:f826e31d18b516f653fe296d967d700fddad5901ae07c622bb3705955e1faa94"},
+    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux2010_x86_64.whl", hash = "sha256:fa130dd50c57d53368c9d59395cb5526eda596d3ffe36666cd81a44d56e48872"},
+    {file = "MarkupSafe-2.0.1-cp36-cp36m-manylinux2014_aarch64.whl", hash = "sha256:905fec760bd2fa1388bb5b489ee8ee5f7291d692638ea5f67982d968366bef9f"},
+    {file = "MarkupSafe-2.0.1-cp36-cp36m-win32.whl", hash = "sha256:6c4ca60fa24e85fe25b912b01e62cb969d69a23a5d5867682dd3e80b5b02581d"},
+    {file = "MarkupSafe-2.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:b2f4bf27480f5e5e8ce285a8c8fd176c0b03e93dcc6646477d4630e83440c6a9"},
+    {file = "MarkupSafe-2.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:0717a7390a68be14b8c793ba258e075c6f4ca819f15edfc2a3a027c823718567"},
+    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux1_i686.whl", hash = "sha256:6557b31b5e2c9ddf0de32a691f2312a32f77cd7681d8af66c2692efdbef84c18"},
+    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:49e3ceeabbfb9d66c3aef5af3a60cc43b85c33df25ce03d0031a608b0a8b2e3f"},
+    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux2010_i686.whl", hash = "sha256:d7f9850398e85aba693bb640262d3611788b1f29a79f0c93c565694658f4071f"},
+    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux2010_x86_64.whl", hash = "sha256:6a7fae0dd14cf60ad5ff42baa2e95727c3d81ded453457771d02b7d2b3f9c0c2"},
+    {file = "MarkupSafe-2.0.1-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:b7f2d075102dc8c794cbde1947378051c4e5180d52d276987b8d28a3bd58c17d"},
+    {file = "MarkupSafe-2.0.1-cp37-cp37m-win32.whl", hash = "sha256:a30e67a65b53ea0a5e62fe23682cfe22712e01f453b95233b25502f7c61cb415"},
+    {file = "MarkupSafe-2.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:611d1ad9a4288cf3e3c16014564df047fe08410e628f89805e475368bd304914"},
+    {file = "MarkupSafe-2.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:be98f628055368795d818ebf93da628541e10b75b41c559fdf36d104c5787066"},
+    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux1_i686.whl", hash = "sha256:1d609f577dc6e1aa17d746f8bd3c31aa4d258f4070d61b2aa5c4166c1539de35"},
+    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:7d91275b0245b1da4d4cfa07e0faedd5b0812efc15b702576d103293e252af1b"},
+    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux2010_i686.whl", hash = "sha256:01a9b8ea66f1658938f65b93a85ebe8bc016e6769611be228d797c9d998dd298"},
+    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:47ab1e7b91c098ab893b828deafa1203de86d0bc6ab587b160f78fe6c4011f75"},
+    {file = "MarkupSafe-2.0.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:97383d78eb34da7e1fa37dd273c20ad4320929af65d156e35a5e2d89566d9dfb"},
+    {file = "MarkupSafe-2.0.1-cp38-cp38-win32.whl", hash = "sha256:023cb26ec21ece8dc3907c0e8320058b2e0cb3c55cf9564da612bc325bed5e64"},
+    {file = "MarkupSafe-2.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:984d76483eb32f1bcb536dc27e4ad56bba4baa70be32fa87152832cdd9db0833"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:2ef54abee730b502252bcdf31b10dacb0a416229b72c18b19e24a4509f273d26"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3c112550557578c26af18a1ccc9e090bfe03832ae994343cfdacd287db6a6ae7"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux1_i686.whl", hash = "sha256:53edb4da6925ad13c07b6d26c2a852bd81e364f95301c66e930ab2aef5b5ddd8"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:f5653a225f31e113b152e56f154ccbe59eeb1c7487b39b9d9f9cdb58e6c79dc5"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux2010_i686.whl", hash = "sha256:4efca8f86c54b22348a5467704e3fec767b2db12fc39c6d963168ab1d3fc9135"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux2010_x86_64.whl", hash = "sha256:ab3ef638ace319fa26553db0624c4699e31a28bb2a835c5faca8f8acf6a5a902"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:f8ba0e8349a38d3001fae7eadded3f6606f0da5d748ee53cc1dab1d6527b9509"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-win32.whl", hash = "sha256:10f82115e21dc0dfec9ab5c0223652f7197feb168c940f3ef61563fc2d6beb74"},
+    {file = "MarkupSafe-2.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:693ce3f9e70a6cf7d2fb9e6c9d8b204b6b39897a2c4a1aa65728d5ac97dcc1d8"},
+    {file = "MarkupSafe-2.0.1.tar.gz", hash = "sha256:594c67807fb16238b30c44bdf74f36c02cdf22d1c8cda91ef8a0ed8dabf5620a"},
+]
 more-itertools = [
     {file = "more-itertools-8.8.0.tar.gz", hash = "sha256:83f0308e05477c68f56ea3a888172c78ed5d5b3c282addb67508e7ba6c8f813a"},
     {file = "more_itertools-8.8.0-py3-none-any.whl", hash = "sha256:2cf89ec599962f2ddc4d568a05defc40e0a587fbc10d5989713638864c36be4d"},
@@ -795,3 +902,7 @@ wcwidth = [
     {file = "wcwidth-0.2.5-py2.py3-none-any.whl", hash = "sha256:beb4802a9cebb9144e99086eff703a642a13d6a0052920003a230f3294bbe784"},
     {file = "wcwidth-0.2.5.tar.gz", hash = "sha256:c4d647b99872929fdb7bdcaa4fbe7f01413ed3d98077df798530e5b04f116c83"},
 ]
+werkzeug = [
+    {file = "Werkzeug-2.0.1-py3-none-any.whl", hash = "sha256:6c1ec500dcdba0baa27600f6a22f6333d8b662d22027ff9f6202e3367413caa8"},
+    {file = "Werkzeug-2.0.1.tar.gz", hash = "sha256:1de1db30d010ff1af14a009224ec49ab2329ad2cde454c8a708130642d579c42"},
+]

pyproject.toml

@@ -18,6 +18,7 @@ requests = "^2.25.1"
 pandas = "^1.2.4"
 fasttext = "^0.9.2"
 pymongo = "^3.11.4"
+Flask = "^2.0.1"
 
 [tool.poetry.dev-dependencies]
 pytest = "^5.2"

sziszapangma/integration/base_asr_service/asr_processor.py

+import os
+import uuid
+from abc import ABC, abstractmethod
+from pathlib import Path
+
+from asr_result import AsrResult
+from flask import Flask, Response, jsonify, request
+
+_TEMP_DIRECTORY = "asr_processing"
+
+
+class AsrProcessor(ABC):
+    def __init__(self):
+        self.read_user_credentials = self.read_user_credentials()
+        self._cached_users_credentials = None
+
+    @abstractmethod
+    def process_asr(self, audio_file_path: str) -> AsrResult:
+        """Method to call for ASR results."""
+
+    def process_request(self) -> Response:
+        file_tag = str(uuid.uuid4())
+        f = request.files["file"]
+        if f is not None and f.filename is not None:
+            file_extension = f.filename.split(".")[-1]
+            file_name = f"{file_tag}.{file_extension}"
+            file_path = f"{_TEMP_DIRECTORY}/{file_name}"
+            f.save(file_path)
+            try:
+                transcription = self.process_asr(file_path)
+                os.remove(file_path)
+                result_object = jsonify(
+                    {"transcription": transcription.words, "full_text": transcription.full_text}
+                )
+            except:
+                result_object = jsonify({"error": "Error on asr processing"})
+        else:
+            result_object = jsonify({"error": "Error on asr processing"})
+        return result_object
+
+    def start_processor(self):
+        app = Flask(__name__)
+        Path(_TEMP_DIRECTORY).mkdir(parents=True, exist_ok=True)
+        app.route("/process_asr", methods=["POST"])(self.process_request)
+        app.run(debug=True, host="0.0.0.0")

sziszapangma/integration/base_asr_service/asr_result.py

+from dataclasses import dataclass
+from typing import List
+
+
+@dataclass(frozen=True)
+class AsrResult:
+    words: List[str]
+    full_text: str

sziszapangma/integration/base_asr_service/requirements.txt

+flask