Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "attention_qkv_bias": false,
+  "codebook_size": 1024,
+  "dim": 1024,
+  "dropout": 0.0,
+  "fast_attention_qkv_bias": false,
+  "fast_dim": 1024,
+  "fast_head_dim": 64,
+  "fast_intermediate_size": 4096,
+  "fast_n_head": 16,
+  "fast_n_local_heads": 2,
+  "head_dim": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_reward_model": false,
+  "max_seq_len": 8192,
+  "model_type": "gpt2",
+  "n_fast_layer": 4,
+  "n_head": 16,
+  "n_layer": 24,
+  "n_local_heads": 2,
+  "norm_eps": 1e-6,
+  "num_codebooks": 8,
+  "rope_base": 1000000.0,
+  "tie_word_embeddings": false,
+  "use_gradient_checkpointing": true,
+  "vocab_size": 102048
+}

firefly-gan-vq-fsq-8x1024-21hz-generator.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e777f440cb041cde17e4daea4a84c58c672e94855ea7023ceed8a7edcab46524
+size 188268196

firefly_gan_vq.yaml

@@ -0,0 +1,33 @@
+_target_: fish_speech.models.vqgan.modules.firefly.FireflyArchitecture
+spec_transform:
+  _target_: fish_speech.utils.spectrogram.LogMelSpectrogram
+  sample_rate: 44100
+  n_mels: 160
+  n_fft: 2048
+  hop_length: 512
+  win_length: 2048
+backbone:
+  _target_: fish_speech.models.vqgan.modules.firefly.ConvNeXtEncoder
+  input_channels: 160
+  depths: [3, 3, 9, 3]
+  dims: [128, 256, 384, 512]
+  drop_path_rate: 0.2
+  kernel_size: 7
+head:
+  _target_: fish_speech.models.vqgan.modules.firefly.HiFiGANGenerator
+  hop_length: 512
+  upsample_rates: [8, 8, 2, 2, 2] # aka. strides
+  upsample_kernel_sizes: [16, 16, 4, 4, 4]
+  resblock_kernel_sizes: [3, 7, 11]
+  resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+  num_mels: 512
+  upsample_initial_channel: 512
+  pre_conv_kernel_size: 13
+  post_conv_kernel_size: 13
+quantizer:
+  _target_: fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize
+  input_dim: 512
+  n_groups: 8
+  n_codebooks: 1
+  levels: [8, 5, 5, 5]
+  downsample_factor: [2, 2]

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54419beca4466c03ce90c11b8948a74ba2cfc508ae2ebdf9f13c6554b27f162a
+size 1275864040

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d985a4b068e76fe888615efb298038ba3e954b91fd4e95271139489650ac875
+size 11481370