# 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: "feature_extractor"
backend: "python"
max_batch_size: 16

parameters [
  {
    key: "num_mel_bins",
    value: { string_value: "80"}
  },
  {
    key: "frame_shift_in_ms"
    value: { string_value: "10"}
  },
  {
    key: "frame_length_in_ms"
    value: { string_value: "25"}
  },
  {
    key: "sample_rate"
    value: { string_value: "16000"}
  },
  {
    key: "cmvn_path"
    value: { string_value: "./model_repo_sense_voice_small/feature_extractor/am.mvn"}
  },
  {
    key: "config_path"
    value: { string_value: "./model_repo_sense_voice_small/feature_extractor/config.yaml"}
  }

]

input [
  {
    name: "wav"
    data_type: TYPE_FP32
    dims: [-1]
  },
  {
    name: "wav_lens"
    data_type: TYPE_INT32
    dims: [1]
  }
]

output [
  {
    name: "speech"
    data_type: TYPE_FP32
    dims: [-1, 560]  # 80
  },
  {
    name: "speech_lengths"
    data_type: TYPE_INT32
    dims: [1]
  }
]

dynamic_batching {
  }

instance_group [
    {
      count: 2
      kind: KIND_GPU
    }
]