Update app.py

app.py

@@ -6,8 +6,6 @@ import time
 import os
 
 BATCH_SIZE = 16
-# TODO: remove token before release and update ckpt path
-TOKEN = os.environ.get("HF_TOKEN", None)
 
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
@@ -17,7 +15,7 @@ model = AutoModelForSpeechSeq2Seq.from_pretrained(
     "openai/whisper-large-v2", torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True, use_flash_attention_2=use_flash_attention_2
 )
 distilled_model = AutoModelForSpeechSeq2Seq.from_pretrained(
-    "sanchit-gandhi/distil-large-v2-private", torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True, use_flash_attention_2=use_flash_attention_2, token=TOKEN
+    "distil-whisper/distil-large-v2", torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True, use_flash_attention_2=use_flash_attention_2, token=TOKEN
 )
 
 if not use_flash_attention_2: