dwohlfahrt
dwohlfahrt
Here's a voice cloning script I put together based on that colab. Works locally on my m4... you know, if you have the patience to wait :) ``` import argparse...
@lucasnewman I haven’t run all that many prompts through my script above, but can confirm that voice cloning worked extremely well on some and not at all in others. What...
Awesome, thanks guys! I'm tied up for the next few hours, but will pull this down and do some comparison testing vs torch this evening.
+1 an mlx layout parser would be huge!
FYI, I just tested with a basic text prompt without providing an image and it works, so it appears the issue is specific to vision/image handling.
Right on. I'll let the king cook! On Wed, Sep 3, 2025 at 3:18 PM Prince Canuma ***@***.***> wrote: > *Blaizzy* left a comment (Blaizzy/mlx-vlm#487) > > > Thanks! >...
Hey @Blaizzy `sequence_number` is part of the OpenAI Responses API spec for streaming responses. See here: https://platform.openai.com/docs/api-reference/responses-streaming/response/created#responses-streaming/response/created-sequence_number. So when trying to consume the this endpoint with streaming responses using the...
As always, thanks a MILLION for all the work you do @Blaizzy. You are a legend in the truest sense of the word 🙏 And now, of course, I have...