Upload folder using huggingface_hub

supertonic3_int8/duration_predictor.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3eb91414d5ff8a7a239b7fe9e34e7e2bf8a8140d8375ffb14718b1c639325db
+size 3700147

supertonic3_int8/model_manifest.json

@@ -0,0 +1,66 @@
+{
+  "duration_predictor.onnx": {
+    "size": 3700147,
+    "sha256": "c3eb91414d5ff8a7a239b7fe9e34e7e2bf8a8140d8375ffb14718b1c639325db"
+  },
+  "text_encoder.onnx": {
+    "size": 36416150,
+    "sha256": "c7befd5ea8c3119769e8a6c1486c4edc6a3bc8365c67621c881bbb774b9902ff"
+  },
+  "vector_estimator_int8_percentile.onnx": {
+    "size": 97017735,
+    "sha256": "0771ae2c47e7a68d54ced662199e9ec2ef5653c7fe6163e3d298d8b547317af7"
+  },
+  "vocoder_prec_percentile.onnx": {
+    "size": 51160880,
+    "sha256": "831ec3e9f82815684ea571820b94a6c562774a479c2de15d9e773d3213b95f49"
+  },
+  "tts.json": {
+    "size": 8253,
+    "sha256": "42078d3aef1cd43ab43021f3c54f47d2d75ceb4e75f627f118890128b06a0d09"
+  },
+  "unicode_indexer.json": {
+    "size": 277676,
+    "sha256": "9bf7346e43883a81f8645c81224f786d43c5b57f3641f6e7671a7d6c493cb24f"
+  },
+  "styles/F1.json": {
+    "size": 292046,
+    "sha256": "bbdec6ee00231c2c742ad05483df5334cab3b52fda3ba38e6a07059c4563dbc2"
+  },
+  "styles/F2.json": {
+    "size": 292423,
+    "sha256": "7c722c6a72707b1a77f035d67f0d1351ba187738e06f7683e8c72b1df3477fc6"
+  },
+  "styles/F3.json": {
+    "size": 290794,
+    "sha256": "12f6ef2573baa2defa1128069cb59f203e3ab67c92af77b42df8a0e3a2f7c6ab"
+  },
+  "styles/F4.json": {
+    "size": 291808,
+    "sha256": "c2fa764c1225a76dfc3e2c73e8aa4f70d9ee48793860eb34c295fff01c2e032b"
+  },
+  "styles/F5.json": {
+    "size": 291479,
+    "sha256": "45966e73316415626cf41a7d1c6f3b4c70dbc1ba2bee5c1978ef0ce33244fc8d"
+  },
+  "styles/M1.json": {
+    "size": 291748,
+    "sha256": "e35604687f5d23694b8e91593a93eec0e4eca6c0b02bb8ed69139ab2ea6b0a5b"
+  },
+  "styles/M2.json": {
+    "size": 292055,
+    "sha256": "b76cbf62bac707c710cf0ae5aba5e31eea1a6339a9734bfae33ab98499534a50"
+  },
+  "styles/M3.json": {
+    "size": 290198,
+    "sha256": "ea1ac35ccb91b0d7ecad533a2fbd0eec10c91513d8951e3b25fbba99954e159b"
+  },
+  "styles/M4.json": {
+    "size": 291522,
+    "sha256": "ca8eefad4fcd989c9379032ff3e50738adc547eeb5e221b82593a6d7b3bac303"
+  },
+  "styles/M5.json": {
+    "size": 291469,
+    "sha256": "dd22b92740314321f8ae11c5e87f8dd60d060f15dd3a632b5adf77f471f77af2"
+  }
+}

supertonic3_int8/text_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7befd5ea8c3119769e8a6c1486c4edc6a3bc8365c67621c881bbb774b9902ff
+size 36416150

supertonic3_int8/tts.json

@@ -0,0 +1,311 @@
+{
+    "tts_version": "v1.7.3",
+    "split": "opensource-multilingual",
+    "ttl": {
+        "latent_dim": 24,
+        "chunk_compress_factor": 6,
+        "batch_expander": {
+            "n_batch_expand": 6
+        },
+        "normalizer": {
+            "scale": 0.25
+        },
+        "text_encoder": {
+            "n_langs": 0,
+            "lang_emb_dim": 0,
+            "text_embedder": {
+                "char_emb_dim": 256
+            },
+            "convnext": {
+                "idim": 256,
+                "ksz": 5,
+                "intermediate_dim": 1024,
+                "num_layers": 6,
+                "dilation_lst": [
+                    1,
+                    1,
+                    2,
+                    2,
+                    4,
+                    4
+                ]
+            },
+            "attn_encoder": {
+                "hidden_channels": 256,
+                "filter_channels": 1024,
+                "n_heads": 4,
+                "n_layers": 4,
+                "p_dropout": 0.0
+            },
+            "proj_out": {
+                "idim": 256,
+                "odim": 256
+            }
+        },
+        "flow_matching": {
+            "sig_min": 1e-08
+        },
+        "style_encoder": {
+            "proj_in": {
+                "ldim": 24,
+                "chunk_compress_factor": 6,
+                "odim": 256
+            },
+            "convnext": {
+                "idim": 256,
+                "ksz": 5,
+                "intermediate_dim": 1024,
+                "num_layers": 6,
+                "dilation_lst": [
+                    1,
+                    1,
+                    1,
+                    1,
+                    1,
+                    1
+                ]
+            },
+            "style_token_layer": {
+                "input_dim": 256,
+                "n_style": 50,
+                "style_key_dim": 256,
+                "style_value_dim": 256,
+                "prototype_dim": 256,
+                "n_units": 256,
+                "n_heads": 2
+            }
+        },
+        "speech_prompted_text_encoder": {
+            "text_dim": 256,
+            "style_dim": 256,
+            "n_units": 256,
+            "n_heads": 2
+        },
+        "uncond_masker": {
+            "prob_both_uncond": 0.04,
+            "prob_text_uncond": 0.01,
+            "std": 0.1,
+            "text_dim": 256,
+            "n_style": 50,
+            "style_key_dim": 256,
+            "style_value_dim": 256
+        },
+        "vector_field": {
+            "n_langs": 0,
+            "lang_emb_dim": 0,
+            "proj_in": {
+                "ldim": 24,
+                "chunk_compress_factor": 6,
+                "odim": 512
+            },
+            "time_encoder": {
+                "time_dim": 64,
+                "hdim": 256
+            },
+            "main_blocks": {
+                "n_blocks": 4,
+                "time_cond_layer": {
+                    "idim": 512,
+                    "time_dim": 64
+                },
+                "style_cond_layer": {
+                    "idim": 512,
+                    "style_dim": 256
+                },
+                "text_cond_layer": {
+                    "idim": 512,
+                    "text_dim": 256,
+                    "n_heads": 8,
+                    "n_units": 512,
+                    "use_residual": true,
+                    "rotary_base": 10000,
+                    "rotary_scale": 10
+                },
+                "convnext_0": {
+                    "idim": 512,
+                    "ksz": 5,
+                    "intermediate_dim": 2048,
+                    "num_layers": 4,
+                    "dilation_lst": [
+                        1,
+                        2,
+                        4,
+                        8
+                    ]
+                },
+                "convnext_1": {
+                    "idim": 512,
+                    "ksz": 5,
+                    "intermediate_dim": 2048,
+                    "num_layers": 1,
+                    "dilation_lst": [
+                        1
+                    ]
+                },
+                "convnext_2": {
+                    "idim": 512,
+                    "ksz": 5,
+                    "intermediate_dim": 2048,
+                    "num_layers": 1,
+                    "dilation_lst": [
+                        1
+                    ]
+                }
+            },
+            "last_convnext": {
+                "idim": 512,
+                "ksz": 5,
+                "intermediate_dim": 2048,
+                "num_layers": 4,
+                "dilation_lst": [
+                    1,
+                    1,
+                    1,
+                    1
+                ]
+            },
+            "proj_out": {
+                "idim": 512,
+                "chunk_compress_factor": 6,
+                "ldim": 24
+            }
+        }
+    },
+    "ae": {
+        "sample_rate": 44100,
+        "n_delay": 0,
+        "base_chunk_size": 512,
+        "chunk_compress_factor": 1,
+        "ldim": 24,
+        "encoder": {
+            "spec_processor": {
+                "n_fft": 2048,
+                "win_length": 2048,
+                "hop_length": 512,
+                "n_mels": 228,
+                "sample_rate": 44100,
+                "eps": 1e-05,
+                "norm_mean": 0.0,
+                "norm_std": 1.0
+            },
+            "ksz_init": 7,
+            "ksz": 7,
+            "num_layers": 10,
+            "dilation_lst": [
+                1,
+                1,
+                1,
+                1,
+                1,
+                1,
+                1,
+                1,
+                1,
+                1
+            ],
+            "intermediate_dim": 2048,
+            "idim": 1253,
+            "hdim": 512,
+            "odim": 24
+        },
+        "decoder": {
+            "ksz_init": 7,
+            "ksz": 7,
+            "num_layers": 10,
+            "dilation_lst": [
+                1,
+                2,
+                4,
+                1,
+                2,
+                4,
+                1,
+                1,
+                1,
+                1
+            ],
+            "intermediate_dim": 2048,
+            "idim": 24,
+            "hdim": 512,
+            "head": {
+                "idim": 512,
+                "hdim": 2048,
+                "odim": 512,
+                "ksz": 3
+            }
+        }
+    },
+    "dp": {
+        "latent_dim": 24,
+        "chunk_compress_factor": 6,
+        "normalizer": {
+            "scale": 1.0
+        },
+        "sentence_encoder": {
+            "char_emb_dim": 64,
+            "text_embedder": {
+                "char_emb_dim": 64
+            },
+            "convnext": {
+                "idim": 64,
+                "ksz": 5,
+                "intermediate_dim": 256,
+                "num_layers": 6,
+                "dilation_lst": [
+                    1,
+                    1,
+                    1,
+                    1,
+                    1,
+                    1
+                ]
+            },
+            "attn_encoder": {
+                "hidden_channels": 64,
+                "filter_channels": 256,
+                "n_heads": 2,
+                "n_layers": 2,
+                "p_dropout": 0.0
+            },
+            "proj_out": {
+                "idim": 64,
+                "odim": 64
+            }
+        },
+        "style_encoder": {
+            "proj_in": {
+                "ldim": 24,
+                "chunk_compress_factor": 6,
+                "odim": 64
+            },
+            "convnext": {
+                "idim": 64,
+                "ksz": 5,
+                "intermediate_dim": 256,
+                "num_layers": 4,
+                "dilation_lst": [
+                    1,
+                    1,
+                    1,
+                    1
+                ]
+            },
+            "style_token_layer": {
+                "input_dim": 64,
+                "n_style": 8,
+                "style_key_dim": 0,
+                "style_value_dim": 16,
+                "prototype_dim": 64,
+                "n_units": 64,
+                "n_heads": 2
+            }
+        },
+        "predictor": {
+            "sentence_dim": 64,
+            "n_style": 8,
+            "style_dim": 16,
+            "hdim": 128,
+            "n_layer": 2
+        }
+    }
+}

supertonic3_int8/vector_estimator_int8_percentile.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0771ae2c47e7a68d54ced662199e9ec2ef5653c7fe6163e3d298d8b547317af7
+size 97017735

supertonic3_int8/vocoder_prec_percentile.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:831ec3e9f82815684ea571820b94a6c562774a479c2de15d9e773d3213b95f49
+size 51160880