Python で音声コンテンツをテキスト形式に変換する方法

python3 -m venv ~/venvs/pytranscribe

source ~/venvs/pytranscribe/bin/activate

(pytranscribe) $

pip install requests==2.24.0

(pytranscribe) $ pip install requests==2.24.0 Collecting requests==2.24.0 Using cached https://files.pythonhosted.org/packages/45/1e/0c169c6a5381e241ba7404532c16a21d86ab872c9bed8bdcd4c423954103/requests-2.24.0-py2.py3-none-any.whl Collecting certifi>=2017.4.17 (from requests==2.24.0) Using cached https://files.pythonhosted.org/packages/5e/c4/6c4fe722df5343c33226f0b4e0bb042e4dc13483228b4718baf286f86d87/certifi-2020.6.20-py2.py3-none-any.whl Collecting urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 (from requests==2.24.0) Using cached https://files.pythonhosted.org/packages/9f/f0/a391d1463ebb1b233795cabfc0ef38d3db4442339de68f847026199e69d7/urllib3-1.25.10-py2.py3-none-any.whl Collecting chardet<4,>=3.0.2 (from requests==2.24.0) Using cached https://files.pythonhosted.org/packages/bc/a9/01ffebfb562e4274b6487b4bb1ddec7ca55ec7510b22e4c51f14098443b8/chardet-3.0.4-py2.py3-none-any.whl Collecting idna<3,>=2.5 (from requests==2.24.0) Using cached https://files.pythonhosted.org/packages/a2/38/928ddce2273eaa564f6f50de919327bf3a00f091b5baba8dfa9460f3a8a8/idna-2.10-py2.py3-none-any.whl Installing collected packages: certifi, urllib3, chardet, idna, requests Successfully installed certifi-2020.6.20 chardet-3.0.4 idna-2.10 requests-2.24.0 urllib3-1.25.10

mkdir pytranscibe cd pytranscribe

export ASSEMBLYAI_KEY=your-api-key-here

import argparse import os import requests API_URL = "https://api.assemblyai.com/v2/" def upload_file_to_api(filename): """Checks for a valid file and then uploads it to AssemblyAI so it can be saved to a secure URL that only that service can access. When the upload is complete we can then initiate the transcription API call. Returns the API JSON if successful, or None if file does not exist. """ if not os.path.exists(filename): return None def read_file(filename, chunk_size=5242880): with open(filename, 'rb') as _file: while True: data = _file.read(chunk_size) if not data: break yield data headers = {'authorization': os.getenv("ASSEMBLYAI_KEY")} response = requests.post("".join([API_URL, "upload"]), headersheaders=headers, data=read_file(filename)) return response.json()

if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("filename") args = parser.parse_args() upload_filename = args.filename response_json = upload_file_to_api(upload_filename) if not response_json: print("file does not exist") else: print("File uploaded to URL: {}".format(response_json['upload_url']))

python upload_audio_file.py FULL_PATH_TO_FILE

File uploaded to URL: https://cdn.assemblyai.com/upload/463ce27f-0922-4ea9-9ce4-3353d84b5638

if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("file_id") args = parser.parse_args() file_id = args.file_id response_json = initiate_transcription(file_id) print(response_json)

# the FILE_IDENTIFIER is returned in the previous step and will # look something like this: 463ce27f-0922-4ea9-9ce4-3353d84b5638 python initiate_transcription.py FILE_IDENTIFIER

{'audio_end_at': None, 'acoustic_model': 'assemblyai_default', 'text': None, 'audio_url': 'https://cdn.assemblyai.com/upload/463ce27f-0922-4ea9-9ce4-3353d84b5638', 'speed_boost': False, 'language_model': 'assemblyai_default', 'redact_pii': False, 'confidence': None, 'webhook_status_code': None, 'id': 'gkuu2krb1-8c7f-4fe3-bb69-6b14a2cac067', 'status': 'queued', 'boost_param': None, 'words': None, 'format_text': True, 'webhook_url': None, 'punctuate': True, 'utterances': None, 'audio_duration': None, 'auto_highlights': False, 'word_boost': [], 'dual_channel': None, 'audio_start_from': None}

import argparse import os import requests API_URL = "https://api.assemblyai.com/v2/" def get_transcription(transcription_id): """Requests the transcription from the API and returns the JSON response.""" endpoint = "".join([API_URL, "transcript/{}".format(transcription_id)]) headers = {"authorization": os.getenv('ASSEMBLYAI_KEY')} response = requests.get(endpoint, headersheaders=headers) return response.json() if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("transcription_id") args = parser.parse_args() transcription_id = args.transcription_id response_json = get_transcription(transcription_id) if response_json['status'] == "completed": for word in response_json['words']: print(word['text'], end=" ") else: print("current status of transcription request: {}".format( response_json['status']))

python get_transcription.py TRANSCRIPTION_ID

current status of transcription request: queued

current status of transcription request: processing

An object relational mapper is a code library that automates the transfer of data stored in relational, databases into objects that are more commonly used in application code or EMS are useful because they provide a high level ...(output abbreviated)