Initial commit: FunASR Speech Recognition Toolkit

Add complete FunASR codebase including models, runtime, and documentation.

runtime/triton_gpu/model_repo_sense_voice_small/encoder/1/model.onnx

@@ -0,0 +1 @@
+/mnt/samsung-t7/yuekai/asr/funaudiollm/SenseVoice/model.onnx

runtime/triton_gpu/model_repo_sense_voice_small/encoder/config.pbtxt

@@ -0,0 +1,71 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.  All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+name: "encoder"
+backend: "onnxruntime"
+default_model_filename: "model.onnx"
+
+max_batch_size: 16
+
+input [
+  {
+    name: "speech"
+    data_type: TYPE_FP32
+    dims: [-1, 560]
+  },
+  {
+    name: "speech_lengths"
+    data_type: TYPE_INT32
+    dims: [1]
+    reshape: { shape: [ ] }
+  },
+  {
+    name: "language"
+    data_type: TYPE_INT32
+    dims: [1]
+    reshape: { shape: [ ] }
+  },
+  {
+    name: "textnorm"
+    data_type: TYPE_INT32
+    dims: [1]
+    reshape: { shape: [ ] }
+  }
+]
+
+output [
+  {
+    name: "ctc_logits"
+    data_type: TYPE_FP32
+    dims: [-1, 25055] 
+  },
+  {
+    name: "encoder_out_lens"
+    data_type: TYPE_INT32
+    dims: [1]
+    reshape: { shape: [ ] }
+  }
+]
+
+dynamic_batching {
+  }
+parameters { key: "cudnn_conv_algo_search" value: { string_value: "2" } }
+
+instance_group [
+    {
+      count: 1
+      kind: KIND_GPU
+    }
+]
+