Upload folder using huggingface_hub

bigvgan_generator.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95ba25972d3de0628d99cd156e9315a9c018899bf739988959ebe3544080ced
+size 449228171

config.yaml

@@ -0,0 +1,72 @@
+semantic_codec:
+    conf:
+        codebook_size: 8192
+        hidden_size: 1024
+        codebook_dim: 8
+        vocos_dim: 384
+        vocos_intermediate_dim: 2048
+        vocos_num_layers: 12
+    checkpoint: semantic_codec.safetensors
+
+s2mel:
+    preprocess_params:
+        sr: 22050
+        spect_params:
+            n_fft: 1024
+            win_length: 1024
+            hop_length: 256
+            n_mels: 80
+            fmin: 0
+            fmax: "None"
+
+    dit_type: "DiT"
+    reg_loss_type: "l1"
+    style_encoder:
+        dim: 192
+    length_regulator:
+        channels: 512
+        is_discrete: false
+        in_channels: 1024
+        content_codebook_size: 2048
+        sampling_ratios: [1, 1, 1, 1]
+        vector_quantize: false
+        n_codebooks: 1
+        quantizer_dropout: 0.0
+        f0_condition: false
+        n_f0_bins: 512
+    DiT:
+        hidden_dim: 512
+        num_heads: 8
+        depth: 13
+        class_dropout_prob: 0.1
+        block_size: 8192
+        in_channels: 80
+        style_condition: true
+        final_layer_type: 'wavenet'
+        target: 'mel'
+        content_dim: 512
+        content_codebook_size: 1024
+        content_type: 'discrete'
+        f0_condition: false
+        n_f0_bins: 512
+        content_codebooks: 1
+        is_causal: false
+        long_skip_connection: true
+        zero_prompt_speech_token: false
+        time_as_token: false
+        style_as_token: false
+        uvit_skip_connection: true
+        add_resblock_in_transformer: false
+    wavenet:
+        hidden_dim: 512
+        num_layers: 8
+        kernel_size: 5
+        dilation_rate: 1
+        p_dropout: 0.2
+        style_condition: true
+
+gpt_checkpoint: gpt.pth
+s2mel_checkpoint: s2mel.pth
+vocoder:
+    type: "bigvgan"
+    name: "nvidia/bigvgan_v2_22khz_80band_256x"

prompt_condition.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929741bfc6dde9350f13e2664f56cf166a58b2a964b6505a97cd8fbb8cdbf58a
+size 1388136

ref_mel.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17af867cef9c6f48b1cb5e57e65a890456c57348dfaa36fa4a9f7223e651438
+size 218217

s2mel.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae1bb12017cbb47e7a5ce537fc82f40b6b1deb71acdb9b8f25686f32714b636
+size 1202198223

semantic_codec.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec947271175d8cad75ec37e83aa487e27c97a0f72a303393772da5ffa84bddf2
+size 177183712

style.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8800c757c2f3bb33ed654ba4c7fd3b4b9184d4b8f318a86c1a09e7da4ae069
+size 2267