Update app.py

app.py

@@ -1,4 +1,30 @@
-import gradio as gr
+from nemo.collections.asr.models import EncDecMultiTaskModel
+
+# Load the Canary-1B model
+canary_model = EncDecMultiTaskModel.from_pretrained('nvidia/canary-1b')
+
+# Define the input manifest file for ASR
+input_manifest = {
+    "audio_filepath": "/path/to/audio.wav",
+    "duration": 1000,  # duration of the audio, can be set to `None` if using NeMo main branch
+    "taskname": "asr",  
+    "source_lang": "en", # language of the audio input, set `source_lang`==`target_lang` for ASR, choices=['en','de','es','fr']
+    "target_lang": "en", # language of the text output, choices=['en','de','es','fr']
+    "pnc": "yes",  # whether to have PnC output, choices=['yes', 'no']
+    "answer": "na", 
+}
+
+# Transcribe audio using the Canary-1B model
+predicted_text = canary_model.transcribe(
+    input_manifest,
+    batch_size=16  # batch size to run the inference with
+)
+
+print("Predicted Text:", predicted_text)
+
+
+
+'''import gradio as gr
 from nemo.collections.asr.models import ASRModel
 import librosa
 
@@ -33,4 +59,4 @@ def transcribe(audio):
 audio_input = gr.components.Audio()
 
 iface = gr.Interface(transcribe, audio_input, "text", title="ASR with NeMo Canary Model")
-iface.launch()
+iface.launch()'''