add vocos config to hub

Dockerfile

@@ -44,6 +44,8 @@ RUN huggingface-cli download BSC-LT/matcha-tts-cat-onnx matcha_multispeaker_cat_
 
 RUN huggingface-cli download BSC-LT/vocos-mel-22khz-onnx  mel_spec_22khz_v2.onnx --local-dir $HOME/app/
 
+RUN huggingface-cli download BSC-LT/vocos-mel-22khz-onnx  config.yaml --local-dir $HOME/app/
+
 COPY --chown=user . $HOME/app/
 
 # Fix ownership issues

config_22khz.yaml

@@ -1,24 +0,0 @@
-feature_extractor:
-  class_path: vocos.feature_extractors.MelSpectrogramFeatures
-  init_args:
-    sample_rate: 22050
-    n_fft: 1024
-    hop_length: 256
-    n_mels: 80
-    padding: center
-
-backbone:
-  class_path: vocos.models.VocosBackbone
-  init_args:
-    input_channels: 80
-    dim: 512
-    intermediate_dim: 1536
-    num_layers: 8
-
-head:
-  class_path: vocos.heads.ISTFTHead
-  init_args:
-    dim: 512
-    n_fft: 1024
-    hop_length: 256
-    padding: center

infer_onnx.py

@@ -33,7 +33,7 @@ def process_text(i: int, text: str, device: torch.device):
 MODEL_PATH_MATCHA_MEL="matcha_multispeaker_cat_opset_15_10_steps_lastwords.onnx"
 MODEL_PATH_MATCHA="matcha_hifigan_multispeaker_cat.onnx"
 MODEL_PATH_VOCOS="mel_spec_22khz_v2.onnx"
-CONFIG_PATH="config_22khz.yaml"
+CONFIG_PATH="config.yaml"
 SPEAKER_ID_DICT="spk_to_id.json"
 
 sess_options = onnxruntime.SessionOptions()