yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-11-03 03:09:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: fix whisper_local indentations docstrings (#6209)

Browse Source 
* whisper_local indentations

* Update whisper_local.py

* fix param docstrings

---------

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
This commit is contained in:
Daria Fokina 2023-11-08 18:15:39 +01:00 committed by GitHub
parent 72cbf3ee0b
commit 08e211f9d6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
haystack/preview/components/audio/whisper_local.py
View File

@ -36,12 +36,9 @@ class LocalWhisperTranscriber:
): ):
""" """
:param model_name_or_path: Name of the model to use. Set it to one of the following values: :param model_name_or_path: Name of the model to use. Set it to one of the following values:
- `tiny` :type model_name_or_path: Literal["tiny", "small", "medium", "large", "large-v2"]
- `small`
- `medium`
- `large`
- `large-v2`
:param device: Name of the torch device to use for inference. If None, CPU is used. :param device: Name of the torch device to use for inference. If None, CPU is used.
:type device: Optional[str]
""" """
whisper_import.check() whisper_import.check()
if model_name_or_path not in get_args(WhisperLocalModel): if model_name_or_path not in get_args(WhisperLocalModel):
@ -78,8 +75,8 @@ class LocalWhisperTranscriber:
[Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper
[github repo](https://github.com/openai/whisper). [github repo](https://github.com/openai/whisper).
:param audio_files: a list of paths or binary streams to transcribe :param audio_files: A list of paths or binary streams to transcribe.
:returns: a list of Documents, one for each file. The content of the document is the transcription text, :returns: A list of Documents, one for each file. The content of the document is the transcription text,
while the document's metadata contains all the other values returned by the Whisper model, such as the while the document's metadata contains all the other values returned by the Whisper model, such as the
alignment data. Another key called `audio_file` contains the path to the audio file used for the alignment data. Another key called `audio_file` contains the path to the audio file used for the
transcription. transcription.
@ -101,8 +98,8 @@ class LocalWhisperTranscriber:
[Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper
[github repo](https://github.com/openai/whisper). [github repo](https://github.com/openai/whisper).
:param audio_files: a list of paths or binary streams to transcribe :param audio_files: A list of paths or binary streams to transcribe.
:returns: a list of Documents, one for each file. The content of the document is the transcription text, :returns: A list of Documents, one for each file. The content of the document is the transcription text,
while the document's metadata contains all the other values returned by the Whisper model, such as the while the document's metadata contains all the other values returned by the Whisper model, such as the
alignment data. Another key called `audio_file` contains the path to the audio file used for the alignment data. Another key called `audio_file` contains the path to the audio file used for the
transcription. transcription.
@ -125,8 +122,8 @@ class LocalWhisperTranscriber:
[Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper
[github repo](https://github.com/openai/whisper). [github repo](https://github.com/openai/whisper).
:param audio_files: a list of paths or binary streams to transcribe :param audio_files: A list of paths or binary streams to transcribe.
:returns: a list of transcriptions. :returns: A list of transcriptions.
""" """
return_segments = kwargs.pop("return_segments", False) return_segments = kwargs.pop("return_segments", False)
transcriptions = [] transcriptions = []