mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
d196646811
This PR addresses an issue in OpenAIWhisperParserLocal where requesting CUDA without availability leads to an AttributeError #15143 Changes: - Refactored Logic for CUDA Availability: The initialization now includes a check for CUDA availability. If CUDA is not available, the code falls back to using the CPU. This ensures seamless operation without manual intervention. - Parameterizing Batch Size and Chunk Size: The batch_size and chunk_size are now configurable parameters, offering greater flexibility and optimization options based on the specific requirements of the use case. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> |
||
---|---|---|
.. | ||
html | ||
language | ||
__init__.py | ||
audio.py | ||
doc_intelligence.py | ||
docai.py | ||
generic.py | ||
grobid.py | ||
msword.py | ||
pdf.py | ||
registry.py | ||
txt.py |