added audio model

CLAP/CLAP_weights_2022.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b917c47fec10547b65cf1d9096e194896fa1c2d6180536c8524289721a4c5b8
+size 2333972488

CLAP/config.yml

@@ -0,0 +1,26 @@
+# TEXT ENCODER CONFIG
+text_model: 'bert-base-uncased'
+text_len: 100
+transformer_embed_dim: 768
+freeze_text_encoder_weights: True
+
+# AUDIO ENCODER CONFIG
+audioenc_name: 'Cnn14'
+out_emb: 2048
+sampling_rate: 44100
+duration: 5
+fmin: 50
+fmax: 14000
+n_fft: 1028
+hop_size: 320
+mel_bins: 64
+window_size: 1024
+
+# PROJECTION SPACE CONFIG 
+d_proj: 1024
+temperature: 0.003
+
+# TRAINING AND EVALUATION CONFIG
+num_classes: 527
+batch_size: 1024
+demo: False

audio_generation/484.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f359e9ea8bcc511637585a475a31972bedc77751e5656fb6a6597995dcb6b8a
+size 7768056443

bigvnat/args.yml

@@ -0,0 +1,63 @@
+resblock: '1'
+num_gpus: 0
+batch_size: 64
+num_mels: 80
+learning_rate: 0.0001
+adam_b1: 0.8
+adam_b2: 0.99
+lr_decay: 0.999
+seed: 1234
+upsample_rates:
+- 4
+- 4
+- 2
+- 2
+- 2
+- 2
+upsample_kernel_sizes:
+- 8
+- 8
+- 4
+- 4
+- 4
+- 4
+upsample_initial_channel: 1536
+resblock_kernel_sizes:
+- 3
+- 7
+- 11
+resblock_dilation_sizes:
+- - 1
+  - 3
+  - 5
+- - 1
+  - 3
+  - 5
+- - 1
+  - 3
+  - 5
+activation: snakebeta
+snake_logscale: true
+resolutions:
+- - 1024
+  - 120
+  - 600
+- - 2048
+  - 240
+  - 1200
+- - 512
+  - 50
+  - 240
+mpd_reshapes:
+- 2
+- 3
+- 5
+- 7
+- 11
+use_spectral_norm: false
+discriminator_channel_mult: 1
+num_workers: 4
+dist_config:
+  dist_backend: nccl
+  dist_url: tcp://localhost:54341
+  world_size: 1

bigvnat/best_netG.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970ca75ee4d5ce583e9396a4534acb14971ea2b4f1c22e038f476680c868a789
+size 449217313

maa2/maa2.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7621db6654b1a96398cf20edd6bc783ba8b7d4bc074e2ac42d609f0426480f19
+size 7308070914