init repo

.gitattributes

@@ -0,0 +1,5 @@
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.pth.tar filter=lfs diff=lfs merge=lfs -text

DAWN_128.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e18bb68888ad3f3ed219ab0be64861c2ec21ae66791e2eac740518fcf954bf
+size 599493862

DAWN_256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0d3316ce238f7cb1eb8cbd8726058e9b29b8c6c5d7ee5d402f2aa749f0843d
+size 599447387

LFG_128_1000ep.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee27780a31c36a8654436458c14acc5eaeb44b40381f2825ac81d4f84026e68f
+size 792382229

LFG_256_400ep.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3c5cd73118c6429a300827b2880e0c264ef8b13d01b27aae01fd4546b89d4a
+size 792382229

hubert_ckp/config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "facebook/hubert-large-ls960-ft",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "transformers_version": "4.10.0.dev0",
+  "vocab_size": 32
+}

hubert_ckp/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

hubert_ckp/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03a1beb2d83abb6a828ab1f72caaf16a43f57a39325b7543c3cb50df5502dce
+size 1534556247

hubert_ckp/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

hubert_ckp/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc55856d3faa99c91b1cb91c6b9717d0d967ea09a676b2b20cff7039169a750
+size 1262396792

hubert_ckp/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}

hubert_ckp/vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}

pbnet_both/checkpoint_100000.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b138f3220df5b87ada54b6455c2d9434e71d0abc59a5e9252d20b8a6be332df8
+size 45264358

pbnet_both/opt.yaml

@@ -0,0 +1,40 @@
+activation: gelu
+archiname: transformerreemb8
+audio_latent_dim: 256
+batch_size: 40
+ckpt: ''
+cuda: true
+dataset: hdtf
+dropout: 0.1
+expname: exps
+eye: 'True'
+ff_size: 128
+first3: false
+folder: exps_delta_pose_rope_eye/HDTF_b40_200_eye_kl1e3_lr4e-4_reg5e-4_rope16_3
+gpu: '0'
+lambda_kl: 0.002
+lambda_rc: 1.0
+lambda_rcw: 1.0
+lambda_reg: 0.0005
+lambda_ssim: 1.0
+lambdas:
+  kl: 0.002
+  rc: 1.0
+  reg: 0.0005
+latent_dim: 256
+losses:
+- rc
+- kl
+- reg
+lr: 0.0004
+max_distance: 128
+max_len: -1
+min_len: -1
+modelname: cvae_transformerreemb8_rc_kl_reg
+modeltype: cvae
+num_buckets: 128
+num_epochs: 100000
+num_frames: 200
+num_layers: 2
+num_seq_max: -1
+snapshot: 10000