From cea42ca470b1dbeecfeee31bf14cce4ad8a621b2 Mon Sep 17 00:00:00 2001
From: Muhammad Shakir <46898829+mshakirDr@users.noreply.github.com>
Date: Sat, 4 Mar 2023 19:12:13 +0100
Subject: [PATCH] Fix hugging face error

Model should be loaded with an id to avoid this error:
huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'pyannote\segmentation'.
---
 whisperx/transcribe.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/whisperx/transcribe.py b/whisperx/transcribe.py
index 88e348d..2efec7a 100644
--- a/whisperx/transcribe.py
+++ b/whisperx/transcribe.py
@@ -639,9 +639,10 @@ def cli():
     if vad_filter:
         if hf_token is None:
             print("Warning, no huggingface token used, needs to be saved in environment variable, otherwise will throw error loading VAD model...")
-        from pyannote.audio import Inference
+        from pyannote.audio import Inference, Model
         vad_pipeline = Inference(
-            "pyannote/segmentation",
+            Model.from_pretrained("pyannote/segmentation",
+                                  use_auth_token=hf_token),
             pre_aggregation_hook=lambda segmentation: segmentation,
             use_auth_token=hf_token,
             device=torch.device(device),