Update app.py

app.py

@@ -1,66 +1,66 @@
-# import gradio as gr
+import gradio as gr
 
-# demo = gr.load("models/leenag/Malasar_Luke_Dict",
-#                examples = [["./luke1.1.wav", "transcribe"],
-#                           ],
-#                title = "VRCLC Malasar Speech Recognition Demo",
-#                description=("Transcribe microphone or audio inputs with the click of a button!"),
-#                cache_examples=False
-#               )
+demo = gr.load("models/leenag/Malasar_Luke_Dict",
+               examples = [["./luke1.1.wav", "transcribe"],
+                          ],
+               title = "VRCLC Malasar Speech Recognition Demo",
+               description=("Transcribe microphone or audio inputs with the click of a button!"),
+               cache_examples=False
+              )
 
-# demo.launch()
-import gradio as gr
-import torch
-import soundfile as sf
-from transformers import pipeline
+demo.launch()
+# import gradio as gr
+# import torch
+# import soundfile as sf
+# from transformers import pipeline
 
-device = "cuda:0" if torch.cuda.is_available() else "cpu"
-pipe = pipeline(
-    "automatic-speech-recognition",
-    model="vrclc/Malasar_medium_MTF",
-    chunk_length_s=10,
-    device=device,
-)
+# device = "cuda:0" if torch.cuda.is_available() else "cpu"
+# pipe = pipeline(
+#     "automatic-speech-recognition",
+#     model="vrclc/Malasar_medium_MTF",
+#     chunk_length_s=10,
+#     device=device,
+# )
 
-def transcribe(audio):
-    """Transcribes Malasar speech from an audio file."""
-    try:
-        if audio is None:
-            return "Please record or upload an audio file."
+# def transcribe(audio):
+#     """Transcribes Malasar speech from an audio file."""
+#     try:
+#         if audio is None:
+#             return "Please record or upload an audio file."
 
-        print(f"[DEBUG] Received audio: {audio}")
+#         print(f"[DEBUG] Received audio: {audio}")
 
-        # Handle filepath case from Gradio
-        audio_path = audio if isinstance(audio, str) else audio.get("name", None)
-        if audio_path is None:
-            return "Could not read audio file."
+#         # Handle filepath case from Gradio
+#         audio_path = audio if isinstance(audio, str) else audio.get("name", None)
+#         if audio_path is None:
+#             return "Could not read audio file."
 
-        print(f"[DEBUG] Reading audio file: {audio_path}")
-        audio_data, sample_rate = sf.read(audio_path)
+#         print(f"[DEBUG] Reading audio file: {audio_path}")
+#         audio_data, sample_rate = sf.read(audio_path)
 
-        print(f"[DEBUG] Audio sample rate: {sample_rate}, shape: {audio_data.shape}")
+#         print(f"[DEBUG] Audio sample rate: {sample_rate}, shape: {audio_data.shape}")
 
-        transcription = pipe(
-            {"array": audio_data, "sampling_rate": sample_rate},
-            chunk_length_s=10,
-            batch_size=8,
-        )["text"]
+#         transcription = pipe(
+#             {"array": audio_data, "sampling_rate": sample_rate},
+#             chunk_length_s=10,
+#             batch_size=8,
+#         )["text"]
 
-        print(f"[DEBUG] Transcription: {transcription}")
-        return transcription
+#         print(f"[DEBUG] Transcription: {transcription}")
+#         return transcription
 
-    except Exception as e:
-        import traceback
-        print("[ERROR] Exception during transcription:")
-        traceback.print_exc()
-        return f"Error: {str(e)}"
+#     except Exception as e:
+#         import traceback
+#         print("[ERROR] Exception during transcription:")
+#         traceback.print_exc()
+#         return f"Error: {str(e)}"
 
-iface = gr.Interface(
-    fn=transcribe,
-    inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
-    outputs="text",
-    title="Malasar Speech Recognition",
-    description="Record or upload Malasar speech and submit to get the transcribed text.",
-    examples=[["luke1.1.wav"]],
-)
-iface.launch()
+# iface = gr.Interface(
+#     fn=transcribe,
+#     inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
+#     outputs="text",
+#     title="Malasar Speech Recognition",
+#     description="Record or upload Malasar speech and submit to get the transcribed text.",
+#     examples=[["luke1.1.wav"]],
+# )
+# iface.launch()