update 2.0

app.py

@@ -12,7 +12,7 @@ import os
 MODEL_NAME = "openai/whisper-medium"
 BATCH_SIZE = 8
 FILE_LIMIT_MB = 1000
-YT_LENGTH_LIMIT_S = 3600  # limit to 1 hour YouTube files
+YT_LENGTH_LIMIT_S = 600  # limit to 1 hour YouTube files
 
 device = 0 if torch.cuda.is_available() else "cpu"
 
@@ -115,11 +115,11 @@ file_transcribe = gr.Interface(
         gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
     outputs="text",
-    title="Whisper Large V3: Transcribe Audio",
+    title="Verbalens Project: Demo 1 prototype",
     description=(
-        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
-        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
-        " of arbitrary length."
+      "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."
     ),
     allow_flagging="never",
 )
@@ -131,10 +131,10 @@ yt_transcribe = gr.Interface(
         gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
     ],
     outputs=["html", "text"],
-    title="Whisper Large V3: Transcribe YouTube",
+    title="Verbalens Project: Demo 1 prototype",
     description=(
-        "Transcribe long-form YouTube videos with the click of a button! Demo uses the checkpoint"
-        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of"
+        "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."
     ),
     allow_flagging="never",

requirements.txt

@@ -2,4 +2,5 @@ transformers
 yt-dlp
 torch
 torchvision
-torchaudio
+torchaudio
+nemo_toolkit