Upload model

config.json

@@ -35,10 +35,11 @@
   "hidden_size": 384,
   "input_dim": 78,
   "is_encoder_decoder": true,
-  "lang_embs": null,
+  "max_source_positions": 5000,
   "model_type": "fastspeech2_conformer",
-  "num_attention_heads": 2,
+  "num_languages": null,
   "num_mel_bins": 80,
+  "num_speakers": null,
   "pad_token_id": 0,
   "pitch_embed_dropout": 0.0,
   "pitch_embed_kernel_size": 1,
@@ -48,7 +49,7 @@
   "pitch_predictor_layers": 5,
   "positionwise_conv_kernel_size": 3,
   "reduction_factor": 1,
-  "should_postnet_compute_logits": false,
+  "speaker_embed_dim": null,
   "speaking_speed": 1.0,
   "speech_decoder_postnet_dropout": 0.5,
   "speech_decoder_postnet_kernel": 5,
@@ -58,11 +59,9 @@
   "stop_gradient_from_pitch_predictor": true,
   "torch_dtype": "float32",
   "transformers_version": "4.31.0.dev0",
-  "use_batch_norm": true,
   "use_cnn_in_conformer": true,
   "use_macaron_style_in_conformer": true,
   "use_masking": true,
   "use_weighted_masking": false,
-  "utt_embed_dim": null,
   "vocab_size": 78
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962c50543eb75ccd9ab6e7e8f5f09e07649e8fbf43001cc8ee3a28666d145ebc
+oid sha256:ba9a9ca759148eee734db773c89ca8502ff84b2f632a8e867759a7d5c2cf2ceb
 size 281214857