Fix commenting and gradio version

README.md

@@ -4,7 +4,7 @@ emoji: 🏆
 colorFrom: pink
 colorTo: indigo
 sdk: gradio
-sdk_version: 5.5.0
+sdk_version: 3.36.1
 app_file: app.py
 pinned: false
 ---

app.py

@@ -50,8 +50,8 @@ def speech_to_speech_translation(audio):
 
 title = "Cascaded STST"
 description = """
-Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in French. Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for speech translation, and Microsoft's
-[SpeechT5 TTS](https://huggingface.co/preetam8/speecht5_finetuned_voxpopuli_fr) model for text-to-speech finetuned for french:
+Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in French. Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for ASR, the 
+[SMaLL-100](https://huggingface.co/alirezamsh/small100) model for text to text translation and Facebook's[MMS TTS-FRA](https://huggingface.co/facebook/mms-tts-fra) for text-to-speech for french:
 
 ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
 """