hotfix 1.4

app.py

@@ -4,7 +4,7 @@ from faster_whisper import WhisperModel
 
 import gradio as gr
 import yt_dlp as youtube_dl
-from transformers import pipeline
+
 from transformers.pipelines.audio_utils import ffmpeg_read
 
 import tempfile
@@ -17,13 +17,6 @@ YT_LENGTH_LIMIT_S = 600  # limit to 1 hour YouTube files
 
 device = 0 if torch.cuda.is_available() else "cpu"
 
-pipe = pipeline(
-    task="automatic-speech-recognition",
-    model=MODEL_NAME,
-    chunk_length_s=30,
-    device=device,
-)
-
 model = WhisperModel(MODEL_NAME, device=device, compute_type="float16" if device == "cuda" else "int8")
 
 @spaces.GPU
@@ -140,9 +133,7 @@ yt_transcribe = gr.Interface(
     outputs=["html", "text"],
     title="Verbalens Project: Demo 1 prototype",
     description=(
-        "Transcribe long-form videos with the click of a button! Demo uses the checkpoint"
-        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}), Nemo Diarization and Transformers to transcribe video files of"
-        " arbitrary length."
+        "Transcribe long-form videos with the click of a button! Demo uses the checkpoint Nemo Diarization and Transformers to transcribe video files of arbitrary length."
     ),
     allow_flagging="never",
 )