-
Notifications
You must be signed in to change notification settings - Fork 322
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Making pipecat work with Krisp #689
Conversation
|
||
#Krisp | ||
KRISP_MODEL_PATH=... |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Easy way to choose which model we wish to use.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I don't see any new environment variables...
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We are using it here inside krisp_filter.py, in case a model path is not provided.
|
||
```shell | ||
source venv/bin/activate | ||
pip install pipecat-ai[krisp] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
While the library has not been published yet, you can test it by creating a local distribution using the PR and then installing it.
Hi @aconchillo , we are going to be able to publish the So, in summary, the At install time, we are going to receive the path to the SDK as an environment variable, and at that point, we will build and install it. So it will work like this:
|
@@ -129,6 +129,24 @@ Pipecat makes use of WebRTC VAD by default when using a WebRTC transport layer. | |||
pip install pipecat-ai[silero] | |||
``` | |||
|
|||
## Running the Krisp Audio Filter |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would say something like ## Reduce background noise with audio filters
(just to make it more attractive) and then a subsection for Krisp.
3. **Export the path to you krisp SDK**: | ||
`export KRISP_SDK_PATH=/PATH/TO/KRISP/SDK` | ||
|
||
### Step 2: Install the `pipecat-krisp` Module |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Any chance the project can be called pipecat-ai-krisp
? Just to match pipecat-ai
. There's another pipecat
project completely unrelated.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The project I mean the pypi package. The repo is fine.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Oh, I see it's already pipecat-ai-krisp
, then I guess just updating this text. :-D
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yep, it seems I have missed this text. 😬
I'd squash this into a single commit probably, or two one for the filter and one for the example. |
LGTM! Just a couple of minor things. This is awesome! |
Great. I will address the missing things and squash in a single commit before merging it. |
Very minor feedback. We already have a 07o foundational example (i.e. |
9640b18
to
e915c67
Compare
Creating Krisp filter for audio processor.