update

Author: gyt1145028706

index.html

@@ -132,7 +132,7 @@ <h1>MOSS-TTS-Nano</h1>
           The model pairs a ~20M-parameter <strong>MOSS-Audio-Tokenizer-Nano</strong>
           with a small LLM for autoregressive token prediction. The tokenizer uses
           a CNN-free, causal Transformer design with RVQ 16 codebooks operating at
-          a 12.5 Hz token stream — achieving 0.125–4 kbps variable bitrate while
+          a 12.5 Hz token stream — achieving 0.125–2 kbps variable bitrate while
           preserving 48 kHz stereo output quality. Voice cloning is driven entirely
           by a short reference clip, with no additional fine-tuning required.
         </p>
@@ -164,7 +164,7 @@ <h2>Key Features</h2>
           </div>
           <div class="feature-item">
             <p class="feature-label">Bitrate</p>
-            <p class="feature-value">0.125–4 kbps</p>
+            <p class="feature-value">0.125–2 kbps</p>
             <p class="feature-desc">Variable bitrate via configurable codebook count.</p>
           </div>
           <div class="feature-item">