Update tiny models for FastSpeech2ConformerModel

config.json

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "FastSpeech2ConformerModel"
+  ],
+  "convolution_bias": true,
+  "decoder_attention_dropout_rate": 0.2,
+  "decoder_concat_after": false,
+  "decoder_config": {
+    "attention_dropout_rate": 0.2,
+    "concat_after": false,
+    "dropout_rate": 0.2,
+    "kernel_size": 31,
+    "layers": 1,
+    "linear_units": 384,
+    "normalize_before": false,
+    "num_attention_heads": 2,
+    "positional_dropout_rate": 0.2
+  },
+  "decoder_dropout_rate": 0.2,
+  "decoder_kernel_size": 31,
+  "decoder_layers": 1,
+  "decoder_linear_units": 384,
+  "decoder_normalize_before": false,
+  "decoder_num_attention_heads": 2,
+  "decoder_positional_dropout_rate": 0.2,
+  "dtype": "float32",
+  "duration_predictor_channels": 256,
+  "duration_predictor_dropout_rate": 0.2,
+  "duration_predictor_kernel_size": 3,
+  "duration_predictor_layers": 1,
+  "encoder_attention_dropout_rate": 0.2,
+  "encoder_concat_after": false,
+  "encoder_config": {
+    "attention_dropout_rate": 0.2,
+    "concat_after": false,
+    "dropout_rate": 0.2,
+    "kernel_size": 7,
+    "layers": 1,
+    "linear_units": 384,
+    "normalize_before": false,
+    "num_attention_heads": 2,
+    "positional_dropout_rate": 0.2
+  },
+  "encoder_dropout_rate": 0.2,
+  "encoder_kernel_size": 7,
+  "encoder_layers": 1,
+  "encoder_linear_units": 384,
+  "encoder_normalize_before": false,
+  "encoder_num_attention_heads": 2,
+  "encoder_positional_dropout_rate": 0.2,
+  "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": 1,
+  "hidden_size": 24,
+  "is_encoder_decoder": true,
+  "max_source_positions": 5000,
+  "model_type": "fastspeech2_conformer",
+  "num_languages": null,
+  "num_mel_bins": 8,
+  "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": 1,
+  "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": 2,
+  "speech_decoder_postnet_units": 128,
+  "stop_gradient_from_energy_predictor": false,
+  "stop_gradient_from_pitch_predictor": true,
+  "transformers_version": "5.16.0.dev0",
+  "use_cnn_in_conformer": true,
+  "use_macaron_style_in_conformer": true,
+  "use_masking": true,
+  "use_weighted_masking": false,
+  "vocab_size": 78
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c8baf64fca611ffccc8def5d83af48f74fa8bb50964c337b6686910224f753
+size 1284220

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<blank>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "77": {
+      "content": "<sos/eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "custom",
+  "bos_token": "<sos/eos>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<sos/eos>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<blank>",
+  "should_strip_spaces": true,
+  "tokenizer_class": "FastSpeech2ConformerTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1 @@
+{"<blank>": 0, "<unk>": 1, "AH0": 2, "N": 3, "T": 4, "D": 5, "S": 6, "R": 7, "L": 8, "DH": 9, "K": 10, "Z": 11, "IH1": 12, "IH0": 13, "M": 14, "EH1": 15, "W": 16, "P": 17, "AE1": 18, "AH1": 19, "V": 20, "ER0": 21, "F": 22, ",": 23, "AA1": 24, "B": 25, "HH": 26, "IY1": 27, "UW1": 28, "IY0": 29, "AO1": 30, "EY1": 31, "AY1": 32, ".": 33, "OW1": 34, "SH": 35, "NG": 36, "G": 37, "ER1": 38, "CH": 39, "JH": 40, "Y": 41, "AW1": 42, "TH": 43, "UH1": 44, "EH2": 45, "OW0": 46, "EY2": 47, "AO0": 48, "IH2": 49, "AE2": 50, "AY2": 51, "AA2": 52, "UW0": 53, "EH0": 54, "OY1": 55, "EY0": 56, "AO2": 57, "ZH": 58, "OW2": 59, "AE0": 60, "UW2": 61, "AH2": 62, "AY0": 63, "IY2": 64, "AW2": 65, "AA0": 66, "'": 67, "ER2": 68, "UH2": 69, "?": 70, "OY2": 71, "!": 72, "AW0": 73, "UH0": 74, "OY0": 75, "..": 76, "<sos/eos>": 77}