Upload FastSpeech2ConformerWithHifiGan

config.json

@@ -1,70 +1,235 @@
 {
   "architectures": [
-    "FastSpeech2ConformerModel"
+    "FastSpeech2ConformerWithHifiGan"
   ],
-  "decoder_config": {
-    "attention_dropout_rate": 0.2,
-    "concat_after": false,
-    "dropout_rate": 0.2,
-    "kernel_size": 31,
-    "layers": 4,
-    "linear_units": 1536,
-    "normalize_before": false,
-    "num_attention_heads": 2,
-    "positional_dropout_rate": 0.2
-  },
-  "duration_predictor_channels": 256,
-  "duration_predictor_dropout_rate": 0.2,
-  "duration_predictor_kernel_size": 3,
-  "duration_predictor_layers": 2,
-  "encoder_config": {
-    "attention_dropout_rate": 0.2,
-    "concat_after": false,
-    "dropout_rate": 0.2,
-    "kernel_size": 7,
-    "layers": 4,
-    "linear_units": 1536,
-    "normalize_before": false,
-    "num_attention_heads": 2,
-    "positional_dropout_rate": 0.2
+  "model_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_config": {
+      "attention_dropout_rate": 0.2,
+      "concat_after": false,
+      "dropout_rate": 0.2,
+      "kernel_size": 31,
+      "layers": 4,
+      "linear_units": 1536,
+      "normalize_before": false,
+      "num_attention_heads": 2,
+      "positional_dropout_rate": 0.2
+    },
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "duration_predictor_channels": 256,
+    "duration_predictor_dropout_rate": 0.2,
+    "duration_predictor_kernel_size": 3,
+    "duration_predictor_layers": 2,
+    "early_stopping": false,
+    "encoder_config": {
+      "attention_dropout_rate": 0.2,
+      "concat_after": false,
+      "dropout_rate": 0.2,
+      "kernel_size": 7,
+      "layers": 4,
+      "linear_units": 1536,
+      "normalize_before": false,
+      "num_attention_heads": 2,
+      "positional_dropout_rate": 0.2
+    },
+    "encoder_layers": 4,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_num_attention_heads": 2,
+    "energy_embed_dropout": 0.0,
+    "energy_embed_kernel_size": 1,
+    "energy_predictor_channels": 256,
+    "energy_predictor_dropout": 0.5,
+    "energy_predictor_kernel_size": 3,
+    "energy_predictor_layers": 2,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 384,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "input_dim": 78,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_source_positions": 5000,
+    "min_length": 0,
+    "model_type": "fastspeech2_conformer",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_languages": null,
+    "num_mel_bins": 80,
+    "num_return_sequences": 1,
+    "num_speakers": null,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "pitch_embed_dropout": 0.0,
+    "pitch_embed_kernel_size": 1,
+    "pitch_predictor_channels": 256,
+    "pitch_predictor_dropout": 0.5,
+    "pitch_predictor_kernel_size": 5,
+    "pitch_predictor_layers": 5,
+    "positionwise_conv_kernel_size": 3,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "reduction_factor": 1,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "speaker_embed_dim": null,
+    "speaking_speed": 1.0,
+    "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,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cnn_in_conformer": true,
+    "use_macaron_style_in_conformer": true,
+    "use_masking": true,
+    "use_weighted_masking": false,
+    "vocab_size": 78
   },
-  "encoder_layers": 4,
-  "encoder_num_attention_heads": 2,
-  "energy_embed_dropout": 0.0,
-  "energy_embed_kernel_size": 1,
-  "energy_predictor_channels": 256,
-  "energy_predictor_dropout": 0.5,
-  "energy_predictor_kernel_size": 3,
-  "energy_predictor_layers": 2,
-  "hidden_size": 384,
-  "input_dim": 78,
-  "is_encoder_decoder": true,
-  "max_source_positions": 5000,
-  "model_type": "fastspeech2_conformer",
-  "num_languages": null,
-  "num_mel_bins": 80,
-  "num_speakers": null,
-  "pitch_embed_dropout": 0.0,
-  "pitch_embed_kernel_size": 1,
-  "pitch_predictor_channels": 256,
-  "pitch_predictor_dropout": 0.5,
-  "pitch_predictor_kernel_size": 5,
-  "pitch_predictor_layers": 5,
-  "positionwise_conv_kernel_size": 3,
-  "reduction_factor": 1,
-  "speaker_embed_dim": null,
-  "speaking_speed": 1.0,
-  "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,
+  "model_type": "fastspeech2_conformer_with_hifigan",
   "torch_dtype": "float32",
   "transformers_version": "4.33.0.dev0",
-  "use_cnn_in_conformer": true,
-  "use_macaron_style_in_conformer": true,
-  "use_masking": true,
-  "use_weighted_masking": false,
-  "vocab_size": 78
+  "vocoder_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.01,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "leaky_relu_slope": 0.1,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_in_dim": 80,
+    "model_type": "hifigan",
+    "no_repeat_ngram_size": 0,
+    "normalize_before": false,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 22050,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2
+    ],
+    "use_bfloat16": false
+  }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa4096f1c4ce019198a7ec8054a7828916bc94b6c6cb968d7723d5a4b808b7a8
-size 281215241
+oid sha256:4c9d7bd71f026b7d60d5e7ec5e92edb5fdabe68ff88dc0cea696c2f2dd7fee0f
+size 336971193