| from key import KEY | |
| from openai import OpenAI | |
| from pathlib import Path | |
| client = OpenAI(api_key=KEY) | |
| audio_file = open(Path(__file__).parent / "saved_model" / "HELLO.mp3", "rb") | |
| transcript = client.audio.transcriptions.create( | |
| model="whisper-1", | |
| file=audio_file, | |
| response_format="verbose_json", | |
| timestamp_granularities=["word"] | |
| ) | |
| print(transcript) | |
| print(transcript.to_json()) | |
| # ❯ /Users/user/models/WhisperReproduction/.venv/bin/python /Users/user/models/WhisperReproduction/main.py | |
| # TranscriptionVerbose(duration=2.559999942779541, language='english', text='Hello, how are you?', segments=None, words=[TranscriptionWord(end=1.2799999713897705, start=0.800000011920929, word='Hello'), TranscriptionWord(end=1.7000000476837158, start=1.2799999713897705, word='how'), TranscriptionWord(end=1.7999999523162842, start=1.7000000476837158, word='are'), TranscriptionWord(end=2.0399999618530273, start=1.7999999523162842, word='you')], task='transcribe') | |
| # /Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/pydantic/main.py:477: UserWarning: Pydantic serializer warnings: | |
| # Expected `str` but got `float` with value `2.559999942779541` - serialized value may not be as expected | |
| # return self.__pydantic_serializer__.to_json( | |
| # { | |
| # "duration": 2.559999942779541, | |
| # "language": "english", | |
| # "text": "Hello, how are you?", | |
| # "words": [ | |
| # { | |
| # "end": 1.2799999713897705, | |
| # "start": 0.800000011920929, | |
| # "word": "Hello" | |
| # }, | |
| # { | |
| # "end": 1.7000000476837158, | |
| # "start": 1.2799999713897705, | |
| # "word": "how" | |
| # }, | |
| # { | |
| # "end": 1.7999999523162842, | |
| # "start": 1.7000000476837158, | |
| # "word": "are" | |
| # }, | |
| # { | |
| # "end": 2.0399999618530273, | |
| # "start": 1.7999999523162842, | |
| # "word": "you" | |
| # } | |
| # ], | |
| # "task": "transcribe" | |
| # } | |
| # audio_file = open(Path(__file__).parent / "saved_model" / "chatgpt_longest_ish.wav", "rb") | |
| # transcript = client.audio.transcriptions.create( | |
| # model="whisper-1", | |
| # file=audio_file | |
| # ) | |
| # Transcription(text='Hello, how are you?') second or less | |
| # Transcription(text='...Of course, there's also computer animation, which has opened up endless possibilities for creativity. What's your favorite type of animation?') 4m 9s | |
| # ❯ /Users/user/models/WhisperReproduction/.venv/bin/python /Users/user/models/WhisperReproduction/main.py | |
| # Traceback (most recent call last): | |
| # File "/Users/user/models/WhisperReproduction/main.py", line 8, in <module> | |
| # transcript = client.audio.transcriptions.create( | |
| # File "/Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/openai/resources/audio/transcriptions.py", line 188, in create | |
| # return self._post( # type: ignore[return-value] | |
| # File "/Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1283, in post | |
| # return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)) | |
| # File "/Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 960, in request | |
| # return self._request( | |
| # File "/Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1049, in _request | |
| # return self._retry_request( | |
| # File "/Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1098, in _retry_request | |
| # return self._request( | |
| # File "/Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1049, in _request | |
| # return self._retry_request( | |
| # File "/Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1098, in _retry_request | |
| # return self._request( | |
| # File "/Users/user/models/WhisperReproduction/.venv/lib/python3.10/site-packages/openai/_base_client.py", line 1064, in _request | |
| # raise self._make_status_error_from_response(err.response) from None | |
| # openai.APIStatusError: Error code: 413 - {'error': {'message': '413: Maximum content size limit (26214400) exceeded (26293319 bytes read)', 'type': 'server_error', 'param': None, 'code': None}} | |
| # ~/models/WhisperReproduction main* 2m 5s | |
| # print(transcript) |