support korean

generate-asr.py

@@ -112,6 +112,11 @@ see https://www.tablesgenerator.com/html_tables#
     <td class="tg-0lax">It supports both English and Chinese.</td>
     <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2">sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2</a></td>
   </tr>
+  <tr>
+    <td class="tg-0pky">sherpa-onnx-x.y.z-arm64-v8a-asr-ko-zipformer.apk</td>
+    <td class="tg-0lax">It supports only Korean. See also <a href="https://github.com/k2-fsa/icefall/pull/1651">https://github.com/k2-fsa/icefall/pull/1651</a></td>
+    <td class="tg-0pky"><a href="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-korean-2024-06-16.tar.bz2">sherpa-onnx-streaming-zipformer-korean-2024-06-16.tar.bz2</a></td>
+  </tr>
   <tr>
     <td class="tg-0pky">sherpa-onnx-x.y.z-arm64-v8a-asr-en-nemo_ctc_80ms.apk</td>
     <td class="tg-0lax">It supports only English. It is converted from <a href="https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_fastconformer_hybrid_large_streaming_80ms">STT En FastConformer Hybrid Transducer-CTC Large Streaming 80ms</a> from <a href="https://github.com/NVIDIA/NeMo/">NVIDIA/NeMo</a>. Note that only the CTC branch is used.</td>