Update app.py

app.py

@@ -7,6 +7,7 @@ import tempfile
 import uuid
 
 import torch
+import tranformers
 
 from nemo.collections.asr.models import ASRModel
 from nemo.collections.asr.parts.utils.streaming_utils import FrameBatchMultiTaskAED
@@ -149,23 +150,6 @@ def on_src_or_tgt_lang_change(src_lang_value, tgt_lang_value, pnc_value):
 			chosen "values" of each Gradio component
 	Returns:
 		src_lang, tgt_lang, pnc - these are the new Gradio components that will be displayed
-	
-	Note: I found the required logic is easier to understand if you think about the possible src & tgt langs as
-	a matrix, e.g. with English, Spanish, French, German as the langs, and only transcription in the same language,
-	and X -> English and English -> X translation being allowed, the matrix looks like the diagram below ("Y" means it is
-	allowed to go into that state).
-	It is easier to understand the code if you think about which state you are in, given the current src_lang_value and
-	tgt_lang_value, and then which states you can go to from there.
-			tgt lang
-			- |EN |ES |FR |DE
-			------------------
-			EN| Y | Y | Y | Y
-			------------------
-		src 	ES| Y | Y |   |
-		lang	------------------
-			FR| Y |   | Y |
-			------------------
-			DE| Y |   |   | Y
 	"""
 
 	if src_lang_value == "English" and tgt_lang_value == "English":
@@ -238,7 +222,7 @@ def on_src_or_tgt_lang_change(src_lang_value, tgt_lang_value, pnc_value):
 
 
 with gr.Blocks(
-	title="NeMo Canary Model",
+	title="MyAlexa",
 	css="""
 		textarea { font-size: 18px;}
 		#model_output_text_box span {
@@ -249,21 +233,17 @@ with gr.Blocks(
 	theme=gr.themes.Default(text_size=gr.themes.sizes.text_lg) # make text slightly bigger (default is text_md )
 ) as demo:
 
-	gr.HTML("<h1 style='text-align: center'>NeMo Canary model: Transcribe & Translate audio</h1>")
+	gr.HTML("<h1 style='text-align: center'>MyAlexa</h1>")
 
 	with gr.Row():
 		with gr.Column():
 			gr.HTML(
-				"<p><b>Step 1:</b> Upload an audio file or record with your microphone.</p>"
-
-				"<p style='color: #A0A0A0;'>This demo supports audio files up to 10 mins long. "
-				"You can transcribe longer files locally with this NeMo "
-				"<a href='https://github.com/NVIDIA/NeMo/blob/main/examples/asr/speech_multitask/speech_to_text_aed_chunked_infer.py'>script</a>.</p>"
+				"<p>Upload an audio file or record with your microphone.</p>"
 			)
 
 			audio_file = gr.Audio(sources=["microphone", "upload"], type="filepath")
 
-			gr.HTML("<p><b>Step 2:</b> Choose the input and output language.</p>")
+			gr.HTML("<p>Choose the input and output language.</p>")
 
 			src_lang = gr.Dropdown(
 				choices=["English", "Spanish", "French", "German"],
@@ -300,14 +280,6 @@ with gr.Blocks(
 			# 	elem_id="llm_output_text_box",
 			# )
 
-	with gr.Row():
-
-		gr.HTML(
-			"<p style='text-align: center'>"
-				"🐤 <a href='https://huggingface.co/nvidia/canary-1b' target='_blank'>Canary model</a> | "
-				"🧑‍💻 <a href='https://github.com/NVIDIA/NeMo' target='_blank'>NeMo Repository</a>"
-			"</p>"
-		)
 
 	go_button.click(
 		fn=transcribe,