add whisper tiny

app.py

@@ -162,7 +162,7 @@ if __name__ == "__main__":
         )
         gr.HTML(
             f"""
-            <p>🚀 <a href="https://huggingface.co/eustlb/distil-large-v3-fr">distil-large-v3-fr</a> is a distilled variant of the <a href="https://huggingface.co/openai/whisper-large-v3">Whisper</a> model by OpenAI. Compared to Whisper, distil-large-v3 runs 6x faster with 50% fewer parameters, while performing to within 1% word error rate (WER) on out-of-distribution evaluation data. It is also faster than the <a href="https://huggingface.co/openai/whisper-tiny">tiniest version of Whisper</a> while being incomparably more accurate (see <a href="https://huggingface.co/eustlb/distil-large-v3-fr#results">results</a>).</p>
+            <p>🚀 <a href="https://huggingface.co/eustlb/distil-large-v3-fr">distil-large-v3-fr</a> is a distilled variant of the <a href="https://huggingface.co/openai/whisper-large-v3">Whisper</a> model by OpenAI. Compared to Whisper, this French ASR distilled model runs 6x faster with 50% fewer parameters, while performing to within 1% word error rate (WER) on out-of-distribution evaluation data. It is also faster than the <a href="https://huggingface.co/openai/whisper-tiny">tiniest version of Whisper</a> while being incomparably more accurate (see <a href="https://huggingface.co/eustlb/distil-large-v3-fr#results">results</a>).</p>
 
             <p>🛠️ In this demo, we perform a speed comparison between: <a href="https://huggingface.co/openai/whisper-large-v3">Whisper large-v3</a>, <a href="https://huggingface.co/openai/whisper-tiny">Whisper tiny</a> and <a href="https://huggingface.co/eustlb/distil-large-v3-fr">distil-large-3-fr</a> to test this claim. Models use the <a href="https://huggingface.co/distil-whisper/distil-large-v3#chunked-long-form">chunked long-form transcription algorithm</a> in 🤗 Transformers.