zjt

.gitattributes

@@ -33,3 +33,5 @@ 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
+*.json filter=lfs diff=lfs merge=lfs -text
+*.jsonl filter=lfs diff=lfs merge=lfs -text

gaudio/audio_encoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75759b2e87f6e8974f86d1d275c6a9d1c96f2a300b32e2c88ee5180331ff558a
+size 884939345

gaudio/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7152eec4e7d795e9c2855fa971dcb22af49fdab01bd2177c41bb6ae5c64fdf
+size 2585

gaudio/preprocessor_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba6754d6c8d51e343d5cd431549cc0aad8f41a4464a23d3dcf3d299859bfe084
+size 604

gaudio/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5b662e421ea9fac075174bb0688ee0d9431699900b90662acd44b2a350503a
+size 695

gaudio/text_encoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9e501c7b83c1fc4f2d2d9ac0c089c4a64029211183a4b3d64394af35f1e7a7
+size 435643029

gaudio/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66
+size 711396

gaudio/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7f777cdd4b947ffa1428b898637bfd00ec9c8fc09fc416645881e5b3dc323c
+size 1289

gdino/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ca35a59ea32610b61561b3dc07c785ff539634223097306b20bd3581a7ce4a
+size 1789

gdino/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f29e24728239929bfc149fb5fe238b3707fddd6048d87d8eaabb38181c79a8b
+size 933400776

gdino_processor/preprocessor_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17fd68afb1f124bfb87a494d409925eec4201b3487c8a694dde64d9ce7109a3
+size 511

gdino_processor/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5b662e421ea9fac075174bb0688ee0d9431699900b90662acd44b2a350503a
+size 695

gdino_processor/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66
+size 711396

gdino_processor/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40ab645b68211910b9170d22433d43186a6ec8ee6fd10ba170524b25bf4fb56
+size 1237

gsam2_image/gsam2_image.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3b1bc43ac04d206b52dc70e9032dc8ed55982d47c8ff5619234c9f349e6d6b
+size 898072910

gsam2_image/gsam2_image.yaml

@@ -0,0 +1,123 @@
+# @package _global_
+
+# Model
+model:
+  _target_: modules.gsam2.sam2.sam2_base.SAM2Base
+  image_encoder:
+    _target_: modules.gsam2.sam2.image_encoder.ImageEncoder
+    scalp: 1
+    trunk:
+      _target_: modules.gsam2.sam2.hieradet.Hiera
+      embed_dim: 144
+      num_heads: 2
+      stages: [2, 6, 36, 4]
+      global_att_blocks: [23, 33, 43]
+      window_pos_embed_bkg_spatial_size: [7, 7]
+      window_spec: [8, 4, 16, 8]
+    neck:
+      _target_: modules.gsam2.sam2.image_encoder.FpnNeck
+      position_encoding:
+        _target_: modules.gsam2.sam2.position_encoding.PositionEmbeddingSine
+        num_pos_feats: 256
+        normalize: true
+        scale: null
+        temperature: 10000
+      d_model: 256
+      backbone_channel_list: [1152, 576, 288, 144]
+      fpn_top_down_levels: [2, 3]  # output level 0 and 1 directly use the backbone features
+      fpn_interp_model: nearest
+
+  memory_attention:
+    _target_: modules.gsam2.sam2.memory_attention.MemoryAttention
+    d_model: 256
+    pos_enc_at_input: true
+    layer:
+      _target_: modules.gsam2.sam2.memory_attention.MemoryAttentionLayer
+      activation: relu
+      dim_feedforward: 2048
+      dropout: 0.1
+      pos_enc_at_attn: false
+      self_attention:
+        _target_: modules.gsam2.sam2.transformer.RoPEAttention
+        rope_theta: 10000.0
+        feat_sizes: [32, 32]
+        embedding_dim: 256
+        num_heads: 1
+        downsample_rate: 1
+        dropout: 0.1
+      d_model: 256
+      pos_enc_at_cross_attn_keys: true
+      pos_enc_at_cross_attn_queries: false
+      cross_attention:
+        _target_: modules.gsam2.sam2.transformer.RoPEAttention
+        rope_theta: 10000.0
+        feat_sizes: [32, 32]
+        rope_k_repeat: True
+        embedding_dim: 256
+        num_heads: 1
+        downsample_rate: 1
+        dropout: 0.1
+        kv_in_dim: 64
+    num_layers: 4
+
+  memory_encoder:
+      _target_: modules.gsam2.sam2.memory_encoder.MemoryEncoder
+      out_dim: 64
+      position_encoding:
+        _target_: modules.gsam2.sam2.position_encoding.PositionEmbeddingSine
+        num_pos_feats: 64
+        normalize: true
+        scale: null
+        temperature: 10000
+      mask_downsampler:
+        _target_: modules.gsam2.sam2.memory_encoder.MaskDownSampler
+        kernel_size: 3
+        stride: 2
+        padding: 1
+      fuser:
+        _target_: modules.gsam2.sam2.memory_encoder.Fuser
+        layer:
+          _target_: modules.gsam2.sam2.memory_encoder.CXBlock
+          dim: 256
+          kernel_size: 7
+          padding: 3
+          layer_scale_init_value: 1e-6
+          use_dwconv: True  # depth-wise convs
+        num_layers: 2
+  sam_mask_decoder_extra_args:
+    dynamic_multimask_via_stability: true
+    dynamic_multimask_stability_delta: 0.05
+    dynamic_multimask_stability_thresh: 0.98
+  num_maskmem: 7
+  image_size: 1024
+  # apply scaled sigmoid on mask logits for memory encoder, and directly feed input mask as output mask
+  sigmoid_scale_for_mem_enc: 20.0
+  sigmoid_bias_for_mem_enc: -10.0
+  use_mask_input_as_output_without_sam: true
+  # Memory
+  directly_add_no_mem_embed: true
+  no_obj_embed_spatial: true
+  # use high-resolution feature map in the SAM mask decoder
+  use_high_res_features_in_sam: true
+  # output 3 masks on the first click on initial conditioning frames
+  multimask_output_in_sam: true
+  # SAM heads
+  iou_prediction_use_sigmoid: True
+  # cross-attend to object pointers from other frames (based on SAM output tokens) in the encoder
+  use_obj_ptrs_in_encoder: true
+  add_tpos_enc_to_obj_ptrs: true
+  proj_tpos_enc_in_obj_ptrs: true
+  use_signed_tpos_enc_to_obj_ptrs: true
+  only_obj_ptrs_in_the_past_for_eval: true
+  # object occlusion prediction
+  pred_obj_scores: true
+  pred_obj_scores_mlp: true
+  fixed_no_obj_ptr: true
+  # multimask tracking settings
+  multimask_output_for_tracking: true
+  use_multimask_token_for_obj_ptr: true
+  multimask_min_pt_num: 0
+  multimask_max_pt_num: 1
+  use_mlp_for_obj_ptr_proj: true
+  # Compilation flag
+  compile_image_encoder: False

gsam2_video/gsam2_video.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3b1bc43ac04d206b52dc70e9032dc8ed55982d47c8ff5619234c9f349e6d6b
+size 898072910

gsam2_video/gsam2_video.yaml

@@ -0,0 +1,125 @@
+model:
+  _target_: modules.gsam2.sam2_video_predictor.SAM2VideoPredictor
+  image_encoder:
+    _target_: modules.gsam2.sam2.image_encoder.ImageEncoder
+    scalp: 1
+    trunk:
+      _target_: modules.gsam2.sam2.hieradet.Hiera
+      embed_dim: 144
+      num_heads: 2
+      stages: [2, 6, 36, 4]
+      global_att_blocks: [23, 33, 43]
+      window_pos_embed_bkg_spatial_size: [7, 7]
+      window_spec: [8, 4, 16, 8]
+    neck:
+      _target_: modules.gsam2.sam2.image_encoder.FpnNeck
+      position_encoding:
+        _target_: modules.gsam2.sam2.position_encoding.PositionEmbeddingSine
+        num_pos_feats: 256
+        normalize: true
+        scale: null
+        temperature: 10000
+      d_model: 256
+      backbone_channel_list: [1152, 576, 288, 144]
+      fpn_top_down_levels: [2, 3]  # output level 0 and 1 directly use the backbone features
+      fpn_interp_model: nearest
+
+  memory_attention:
+    _target_: modules.gsam2.sam2.memory_attention.MemoryAttention
+    d_model: 256
+    pos_enc_at_input: true
+    layer:
+      _target_: modules.gsam2.sam2.memory_attention.MemoryAttentionLayer
+      activation: relu
+      dim_feedforward: 2048
+      dropout: 0.1
+      pos_enc_at_attn: false
+      self_attention:
+        _target_: modules.gsam2.sam2.transformer.RoPEAttention
+        rope_theta: 10000.0
+        feat_sizes: [32, 32]
+        embedding_dim: 256
+        num_heads: 1
+        downsample_rate: 1
+        dropout: 0.1
+      d_model: 256
+      pos_enc_at_cross_attn_keys: true
+      pos_enc_at_cross_attn_queries: false
+      cross_attention:
+        _target_: modules.gsam2.sam2.transformer.RoPEAttention
+        rope_theta: 10000.0
+        feat_sizes: [32, 32]
+        rope_k_repeat: True
+        embedding_dim: 256
+        num_heads: 1
+        downsample_rate: 1
+        dropout: 0.1
+        kv_in_dim: 64
+    num_layers: 4
+
+  memory_encoder:
+      _target_: modules.gsam2.sam2.memory_encoder.MemoryEncoder
+      out_dim: 64
+      position_encoding:
+        _target_: modules.gsam2.sam2.position_encoding.PositionEmbeddingSine
+        num_pos_feats: 64
+        normalize: true
+        scale: null
+        temperature: 10000
+      mask_downsampler:
+        _target_: modules.gsam2.sam2.memory_encoder.MaskDownSampler
+        kernel_size: 3
+        stride: 2
+        padding: 1
+      fuser:
+        _target_: modules.gsam2.sam2.memory_encoder.Fuser
+        layer:
+          _target_: modules.gsam2.sam2.memory_encoder.CXBlock
+          dim: 256
+          kernel_size: 7
+          padding: 3
+          layer_scale_init_value: 1e-6
+          use_dwconv: True  # depth-wise convs
+        num_layers: 2
+
+  sam_mask_decoder_extra_args:
+    dynamic_multimask_via_stability: true
+    dynamic_multimask_stability_delta: 0.05
+    dynamic_multimask_stability_thresh: 0.98
+  # the sigmoid mask logits on interacted frames with clicks in the memory encoder so that the encoded masks are exactly as what users see from clicking
+  binarize_mask_from_pts_for_mem_enc: true
+  # fill small holes in the low-res masks up to `fill_hole_area` (before resizing them to the original video resolution)
+  fill_hole_area: 8
+  num_maskmem: 7
+  image_size: 1024
+  # apply scaled sigmoid on mask logits for memory encoder, and directly feed input mask as output mask
+  sigmoid_scale_for_mem_enc: 20.0
+  sigmoid_bias_for_mem_enc: -10.0
+  use_mask_input_as_output_without_sam: true
+  # Memory
+  directly_add_no_mem_embed: true
+  no_obj_embed_spatial: true
+  # use high-resolution feature map in the SAM mask decoder
+  use_high_res_features_in_sam: true
+  # output 3 masks on the first click on initial conditioning frames
+  multimask_output_in_sam: true
+  # SAM heads
+  iou_prediction_use_sigmoid: True
+  # cross-attend to object pointers from other frames (based on SAM output tokens) in the encoder
+  use_obj_ptrs_in_encoder: true
+  add_tpos_enc_to_obj_ptrs: true
+  proj_tpos_enc_in_obj_ptrs: true
+  use_signed_tpos_enc_to_obj_ptrs: true
+  only_obj_ptrs_in_the_past_for_eval: true
+  # object occlusion prediction
+  pred_obj_scores: true
+  pred_obj_scores_mlp: true
+  fixed_no_obj_ptr: true
+  # multimask tracking settings
+  multimask_output_for_tracking: true
+  use_multimask_token_for_obj_ptr: true
+  multimask_min_pt_num: 0
+  multimask_max_pt_num: 1
+  use_mlp_for_obj_ptr_proj: true
+  # Compilation flag
+  compile_image_encoder: False

llama/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7941a3d70fc216b82de7df97863937dcd33e644416665b89dbdc67b1daa66a
+size 928

llama/generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4beaeab19fc8c2d4b0725864a97f73bf787b1bd4bec222cc9e1e6a8030ca9c
+size 230

llama/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477ff93289f45ff953aa9f7ce6331d5fce4ee466f53865301333ea0ccece72dd
+size 4976698592

llama/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8899cf9adf52f3fa093a6469f4efaecf66d9b62317eddde424ae8358d704a05b
+size 4999802616

llama/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe29f6c7b95a76fafb3f9dcd614f036f41f44c19ff2e4cf58a9e2ccf442e10b1
+size 4915916080

llama/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013bc9e3d5d06232d8a358ad3cd323b732255d31e2debe3bf0c6325b88110ae0
+size 1168138808

llama/model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b
+size 23950

sensevoice/am.mvn

@@ -0,0 +1,8 @@
+<Nnet>
+<Splice> 400 400
+[ 0 ]
+<AddShift> 400 400
+<LearnRateCoef> 0 [ -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 ]
+<Rescale> 400 400
+<LearnRateCoef> 0 [ 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 ]
+</Nnet>

sensevoice/chn_jpn_yue_eng_ko_spectok.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa87f86064c3730d799ddf7af3c04659151102cba548bce325cf06ba4da4e6a8
+size 377341

sensevoice/sensevoice.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6280b847a0ec99377af351999a2d2223d005dd3161d4005328db35820d6f91d
+size 938091356

sensevoice/sensevoice.yaml

@@ -0,0 +1,200 @@
+model:
+  _target_: modules.sensevoice.model.SenseVoice
+  model:
+    _target_: modules.sensevoice.sensevoicesmall.SenseVoiceSmall
+    specaug: 
+      _target_: modules.sensevoice.specaug.SpecAugLFR
+      apply_freq_mask: true
+      apply_time_mask: true
+      apply_time_warp: false
+      freq_mask_width_range: [0, 30]
+      lfr_rate: 6
+      num_freq_mask: 1
+      num_time_mask: 1
+      time_mask_width_range: [0, 12]
+      time_warp_mode: bicubic
+      time_warp_window: 5
+    encoder: 
+      _target_: modules.sensevoice.sensevoicesmall.SenseVoiceEncoderSmall
+      attention_dropout_rate: 0.1
+      attention_heads: 4
+      dropout_rate: 0.1
+      kernel_size: 11
+      linear_units: 2048
+      normalize_before: true
+      num_blocks: 50
+      output_size: 512
+      sanm_shfit: 0
+      tp_blocks: 20
+      input_size: 560
+    tokenizer:
+      _target_: modules.sensevoice.tokenizer.SentencepiecesTokenizer
+      bpemodel: /storage-root/datasets/zhaojingtong/checkpoints/sensevoice/chn_jpn_yue_eng_ko_spectok.bpe.model
+      unk_symbol: <unk>
+      split_with_space: true
+    frontend:
+      _target_: modules.sensevoice.frontend.WavFrontend
+      fs: 16000
+      window: hamming
+      n_mels: 80
+      frame_length: 25
+      frame_shift: 10
+      lfr_m: 7
+      lfr_n: 6
+    length_normalized_loss: true
+    input_size: 560
+    vocab_size: 25055
+    sos: 1
+    eos: 2
+    ignore_id: -1
+  vad_model: 
+    _target_: modules.sensevoice.vad.FsmnVADStreaming
+    encoder:
+      _target_: modules.sensevoice.vad.FSMN
+      input_dim: 400
+      input_affine_dim: 140
+      fsmn_layers: 4
+      linear_dim: 250
+      proj_dim: 128
+      lorder: 20
+      rorder: 0
+      lstride: 1
+      rstride: 0
+      output_affine_dim: 140
+      output_dim: 248
+    frontend: 
+      _target_: modules.sensevoice.frontend.WavFrontendOnline
+      fs: 16000
+      window: hamming
+      n_mels: 80
+      frame_length: 25
+      frame_shift: 10
+      dither: 0.0
+      lfr_m: 5
+      lfr_n: 1
+      cmvn_file: /storage-root/datasets/zhaojingtong/checkpoints/sensevoice/am.mvn
+    sample_rate: 16000
+    detect_mode: 1 
+    snr_mode: 0
+    max_end_silence_time: 800
+    max_start_silence_time: 3000
+    do_start_point_detection: True
+    do_end_point_detection: True
+    window_size_ms: 200
+    sil_to_speech_time_thres: 150
+    speech_to_sil_time_thres: 150
+    speech_2_noise_ratio: 1.0
+    do_extend: 1
+    lookback_time_start_point: 200
+    lookahead_time_end_point: 100
+    max_single_segment_time: 60000
+    snr_thres: -100.0
+    noise_frame_num_used_for_snr: 100
+    decibel_thres: -100.0
+    speech_noise_thres: 0.6
+    fe_prior_thres: 0.0001
+    silence_pdf_num: 1
+    sil_pdf_ids: [0]
+    speech_noise_thresh_low: -0.1
+    speech_noise_thresh_high: 0.3
+    output_frame_probs: False
+    frame_in_ms: 10
+    frame_length_ms: 25
+    tokenizer: None
+    vocab_size: -1
+    input_size: 400
+  kwargs:
+    specaug:
+      apply_freq_mask: true
+      apply_time_mask: true
+      apply_time_warp: false
+      freq_mask_width_range: [0, 30]
+      lfr_rate: 6
+      num_freq_mask: 1
+      num_time_mask: 1
+      time_mask_width_range: [0, 12]
+      time_warp_mode: bicubic
+      time_warp_window: 5
+    encoder:
+      attention_dropout_rate: 0.1
+      attention_heads: 4
+      dropout_rate: 0.1
+      kernel_size: 11
+      linear_units: 2048
+      normalize_before: true
+      num_blocks: 50
+      output_size: 512
+      sanm_shfit: 0
+      tp_blocks: 20
+      input_size: 560
+    tokenizer:
+      bpemodel: /storage-root/datasets/zhaojingtong/checkpoints/sensevoice/chn_jpn_yue_eng_ko_spectok.bpe.model
+      unk_symbol: <unk>
+      split_with_space: true
+    frontend:
+      fs: 16000
+      window: hamming
+      n_mels: 80
+      frame_length: 25
+      frame_shift: 10
+      lfr_m: 7
+      lfr_n: 6
+    length_normalized_loss: true
+    input_size: 560
+    vocab_size: 25055
+    sos: 1
+    eos: 2
+    ignore_id: -1
+  vad_kwargs:
+    encoder:
+      input_dim: 400
+      input_affine_dim: 140
+      fsmn_layers: 4
+      linear_dim: 250
+      proj_dim: 128
+      lorder: 20
+      rorder: 0
+      lstride: 1
+      rstride: 0
+      output_affine_dim: 140
+      output_dim: 248
+    frontend: 
+      fs: 16000
+      window: hamming
+      n_mels: 80
+      frame_length: 25
+      frame_shift: 10
+      dither: 0.0
+      lfr_m: 5
+      lfr_n: 1
+      cmvn_file: /storage-root/datasets/zhaojingtong/checkpoints/sensevoice/am.mvn
+    sample_rate: 16000
+    detect_mode: 1 
+    snr_mode: 0
+    max_end_silence_time: 800
+    max_start_silence_time: 3000
+    do_start_point_detection: True
+    do_end_point_detection: True
+    window_size_ms: 200
+    sil_to_speech_time_thres: 150
+    speech_to_sil_time_thres: 150
+    speech_2_noise_ratio: 1.0
+    do_extend: 1
+    lookback_time_start_point: 200
+    lookahead_time_end_point: 100
+    max_single_segment_time: 60000
+    snr_thres: -100.0
+    noise_frame_num_used_for_snr: 100
+    decibel_thres: -100.0
+    speech_noise_thres: 0.6
+    fe_prior_thres: 0.0001
+    silence_pdf_num: 1
+    sil_pdf_ids: [0]
+    speech_noise_thresh_low: -0.1
+    speech_noise_thresh_high: 0.3
+    output_frame_probs: False
+    frame_in_ms: 10
+    frame_length_ms: 25
+    tokenizer: None
+    vocab_size: -1
+    input_size: 400

siglip/siglip.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3afbb189b33a42a2ef804a388fa88aea293741949a6cdd61035eeb094139bff1
+size 1713053358

siglip/siglip.yaml

@@ -0,0 +1,29 @@
+model:
+  _target_: modules.siglip.ImageEncoder
+  embeddings:
+    _target_: modules.siglip.SiglipVisionEmbeddings
+    hidden_size: 1152
+    image_size: 384
+    patch_size: 14
+    num_channels: 3
+  encoder:
+    _target_: modules.siglip.SiglipEncoder
+    hidden_size: 1152
+    num_attention_heads: 16
+    attention_dropout: 0.0
+    hidden_act: gelu_pytorch_tanh
+    intermediate_size: 4304
+    layer_norm_eps: 1e-6
+    num_hidden_layers: 27
+  head:
+    _target_: modules.siglip.SiglipMultiheadAttentionPoolingHead
+    mlp: 
+      _target_: modules.siglip.SiglipMLP
+      hidden_act: gelu_pytorch_tanh
+      hidden_size: 1152
+      intermediate_size: 4304
+    hidden_size: 1152
+    num_attention_heads: 16
+    layer_norm_eps: 1e-6
+  hidden_size: 1152
+  layer_norm_eps: 1e-6

sv_encoder/sv_encoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75759b2e87f6e8974f86d1d275c6a9d1c96f2a300b32e2c88ee5180331ff558a
+size 884939345

sv_encoder/sv_encoder.yaml

@@ -0,0 +1,33 @@
+model:
+  _target_: modules.gaudio.sv_encoder.SenseVoiceSmall
+  specaug: 
+    _target_: modules.gaudio.sv_encoder.SpecAugLFR
+    apply_freq_mask: true
+    apply_time_mask: true
+    apply_time_warp: false
+    freq_mask_width_range: [0, 30]
+    lfr_rate: 6
+    num_freq_mask: 1
+    num_time_mask: 1
+    time_mask_width_range: [0, 12]
+    time_warp_mode: bicubic
+    time_warp_window: 5
+  encoder: 
+    _target_: modules.gaudio.sv_encoder.SenseVoiceEncoderSmall
+    attention_dropout_rate: 0.1
+    attention_heads: 4
+    dropout_rate: 0.1
+    kernel_size: 11
+    linear_units: 2048
+    normalize_before: true
+    num_blocks: 50
+    output_size: 512
+    sanm_shfit: 0
+    tp_blocks: 20
+    input_size: 560
+  length_normalized_loss: true
+  input_size: 560
+  vocab_size: 25055
+  sos: 1
+  eos: 2
+  ignore_id: -1

tokenizer/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73565d76ce52078f48b8cd9a5ab59615c5519704c2fa6f52c5f6309915a70e7
+size 480

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200a2a14d4927029e80613d8f4f770359e5910d931906c5d1d195dcdae9c6828
+size 17209899

tokenizer/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95faea2e162d6f8336ccaebaff5e94b779e279673c8bb13a7f0d427162fb7ef7
+size 55400