Community: added audio-parser RemoteFasterWhisperParser in audio.py #26638
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Skipped Deployment
|
dosubot
bot
added
size:L
lfenzo
changed the title
lfenzo
force-pushed
the
remote-faster-whisper
branch
from
58d08f2 to
362ea98
Compare
lfenzo
force-pushed
the
remote-faster-whisper
branch
from
362ea98 to
581115a
Compare
|
Marking as stale and still in need of support, per the review process |
lfenzo
force-pushed
the
remote-faster-whisper
branch
3 times, most recently
from
adb3287 to
78576cf
Compare
lfenzo
force-pushed
the
remote-faster-whisper
branch
from
78576cf to
9ff7392
Compare
lfenzo
changed the title
efriis
reviewed
Dec 11, 2024
| RuntimeError: If the transcription process fails. | ||
| """ | ||
|
|
||
| process = subprocess.Popen( |
There was a problem hiding this comment.
unfortunately this isn't acceptable for security reasons, so will close!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR introduces a new audio parser to Langchain that allows interaction with Faster Whisper running in a remote server. This enhancement addresses a significant issue with the current Faster Whisper integration, which requires the Langchain process to have all necessary GPU drivers and dependencies installed locally. In microservice-based architectures, this leads to heavy and redundant dependencies in the Langchain container, making deployment more complex and resource-intensive.
Solution
This PR solves this issue by introducing a remote audio parser that can communicate with faster-whisper-server running in a dedicated container. This allows Langchain to delegate audio transcription tasks to this remote server, eliminating the need for GPU dependencies within the Langchain container itself reducing its dependency footprint.
The implementation relies on Python's built-in
subprocessmodule to handle communication with the remote server, ensuring that no extra dependencies are introduced in Langchain.cc.: @eyurtsev