Upload model

config.json

@@ -1,5 +1,4 @@
 {
-  "acoustic_dim": 384,
   "architectures": [
     "FastSpeech2ConformerModel"
   ],
@@ -31,11 +30,12 @@
   "energy_predictor_kernel_size": 3,
   "energy_predictor_layers": 2,
   "eos_token_id": 2,
+  "hidden_size": 384,
   "input_dim": 78,
   "lang_embs": null,
   "model_type": "fastspeech2_conformer",
   "num_attention_heads": 2,
-  "output_dim": 80,
+  "num_mel_bins": 80,
   "pad_token_id": 1,
   "pitch_embed_dropout": 0.0,
   "pitch_embed_kernel_size": 1,
@@ -44,11 +44,12 @@
   "pitch_predictor_kernel_size": 5,
   "pitch_predictor_layers": 5,
   "positionwise_conv_kernel_size": 3,
-  "postnet_channels": 256,
-  "postnet_dropout_rate": 0.5,
-  "postnet_filters": 5,
-  "postnet_layers": 5,
   "reduction_factor": 1,
+  "should_postnet_compute_logits": false,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
   "stop_gradient_from_energy_predictor": false,
   "stop_gradient_from_pitch_predictor": true,
   "torch_dtype": "float32",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edff08e1cbec2744f4d0d6edb8ee380cd54dc4b09a123a6cd39691bad49deda4
-size 281200269
+oid sha256:400dbf7da859e4f8ccda2aa161d0e0344cc58a772fa9b4d2b6fcef3a12347233
+size 281214473