Adjusting notes

app.py

@@ -109,13 +109,19 @@ transcribe = gr.Interface(
     outputs=gr.Textbox(label="Transcription", lines=15),
     title="Latvian speech recognition: Transcribe Audio",
     description=("""
-        Test Latvian speech recognition (STT) models. Three models are available:
+        Test Latvian speech recognition (STT) models. Three models are available on this demo.
+        
+        <h2>tiny</h2>
+        
+        [RaivisDejus/whisper-tiny-lv](https://huggingface.co/RaivisDejus/whisper-tiny-lv) - Fastest, requiring least RAM, but also poor accuracy. On this demo hardware 30 second audio will take ~45 seconds to transcribe.
+        
+        <h2>small</h2>
         
-        * [tiny](https://huggingface.co/RaivisDejus/whisper-tiny-lv) - Fastest, requiring least RAM, but also poor accuracy. On this demo hardware 30 second audio will take ~45 seconds to transcribe.
+        [RaivisDejus/whisper-small-lv](https://huggingface.co/RaivisDejus/whisper-small-lv) - Reasonably fast, reasonably accurate, requiring reasonable amounts of RAM. On this demo hardware 30 second audio will take ~1 minute to transcribe.
         
-        * [small](https://huggingface.co/RaivisDejus/whisper-small-lv) - Reasonably fast, reasonably accurate, requiring reasonable amounts of RAM. On this demo hardware 30 second audio will take ~1 minute to transcribe.
+        <h2>large</h2>
         
-        * [large](https://huggingface.co/AiLab-IMCS-UL/whisper-large-v3-lv-late-cv17) - Most accurate, developed by scientists from [ailab.lv](https://ailab.lv/). Requires most RAM and for best performance should be run on a GPU. On this demo hardware 30 second audio will take ~4 minutes to transcribe.
+        [AiLab-IMCS-UL/whisper-large-v3-lv-late-cv17](https://huggingface.co/AiLab-IMCS-UL/whisper-large-v3-lv-late-cv17) - Most accurate, developed by scientists from [ailab.lv](https://ailab.lv/). Requires most RAM and for best performance should be run on a GPU. On this demo hardware 30 second audio will take ~4 minutes to transcribe.
         
         To improve speech recognition quality, more data is needed, add your voice on [Balsu talka](https://balsutalka.lv/)
         """