update

README.md

@@ -26,9 +26,9 @@ extra_gated_fields:
 [![zhihu](https://img.shields.io/badge/知乎-0079FF.svg?logo=zhihu&logoColor=white)](https://zhuanlan.zhihu.com/p/2253009511)
 [![DAWN](https://img.shields.io/badge/Github-181717?style=plastic&logo=github&logoColor=white)](https://github.com/Hanbo-Cheng/DAWN-pytorch)
 
-`./hubert_ckpt`: hubert audio encoder, same as [hubert-base](https://huggingface.co/facebook/hubert-base-ls960)
+`./hubert_ckpt`: you need to download [hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft/tree/main)
 
-`./pbnet_both/checkpoint_100000.pth.tar`: checkpoint for the Pose-Blink generation network 
+`./pbnet`: checkpoint for the Pose-Blink generation network 
 
 `DAWN_128.pth`: checkpoint for the A2V-FDM with 128 * 128 resolution
 

hubert_ckp/config.json

@@ -1,70 +0,0 @@
-{
-  "_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

@@ -1,9 +0,0 @@
-{
-  "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

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

hubert_ckp/special_tokens_map.json

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

hubert_ckp/tf_model.h5

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

hubert_ckp/tokenizer_config.json

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

hubert_ckp/vocab.json

@@ -1 +0,0 @@
-{"<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

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

pbnet_both/opt.yaml

@@ -1,40 +0,0 @@
-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