Spaces:
Runtime error
Runtime error
Upload 11 files
Browse files- ckpt/README.md +14 -0
- ckpt/chinese-hubert-large/chinese-hubert-large_config.json +71 -0
- ckpt/chinese-hubert-large/chinese-hubert-large_preprocessor_config.json +9 -0
- ckpt/chinese-hubert-large/pytorch_model.bin +3 -0
- ckpt/gitattributes +35 -0
- ckpt/stage1.ckpt +3 -0
- ckpt/stage2_audio_only_hubert.ckpt +3 -0
- ckpt/stage2_full_control_hubert.ckpt +3 -0
- ckpt/stage2_full_control_mfcc.ckpt +3 -0
- ckpt/stage2_pose_only_hubert.ckpt +3 -0
- ckpt/stage2_pose_only_mfcc.ckpt +3 -0
ckpt/README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
---
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
remain to be done
|
| 9 |
+
|
| 10 |
+
## Model Details
|
| 11 |
+
|
| 12 |
+
### Model Description
|
| 13 |
+
|
| 14 |
+
remain to be done
|
ckpt/chinese-hubert-large/chinese-hubert-large_config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.1,
|
| 3 |
+
"apply_spec_augment": true,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"HubertModel"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"classifier_proj_size": 256,
|
| 10 |
+
"conv_bias": false,
|
| 11 |
+
"conv_dim": [
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512
|
| 19 |
+
],
|
| 20 |
+
"conv_kernel": [
|
| 21 |
+
10,
|
| 22 |
+
3,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
2,
|
| 27 |
+
2
|
| 28 |
+
],
|
| 29 |
+
"conv_stride": [
|
| 30 |
+
5,
|
| 31 |
+
2,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2
|
| 37 |
+
],
|
| 38 |
+
"ctc_loss_reduction": "sum",
|
| 39 |
+
"ctc_zero_infinity": false,
|
| 40 |
+
"do_stable_layer_norm": true,
|
| 41 |
+
"eos_token_id": 2,
|
| 42 |
+
"feat_extract_activation": "gelu",
|
| 43 |
+
"feat_extract_norm": "layer",
|
| 44 |
+
"feat_proj_dropout": 0.0,
|
| 45 |
+
"feat_proj_layer_norm": true,
|
| 46 |
+
"final_dropout": 0.1,
|
| 47 |
+
"hidden_act": "gelu",
|
| 48 |
+
"hidden_dropout": 0.1,
|
| 49 |
+
"hidden_size": 1024,
|
| 50 |
+
"initializer_range": 0.02,
|
| 51 |
+
"intermediate_size": 4096,
|
| 52 |
+
"layer_norm_eps": 1e-05,
|
| 53 |
+
"layerdrop": 0.1,
|
| 54 |
+
"mask_feature_length": 10,
|
| 55 |
+
"mask_feature_min_masks": 0,
|
| 56 |
+
"mask_feature_prob": 0.0,
|
| 57 |
+
"mask_time_length": 10,
|
| 58 |
+
"mask_time_min_masks": 2,
|
| 59 |
+
"mask_time_prob": 0.05,
|
| 60 |
+
"model_type": "hubert",
|
| 61 |
+
"num_attention_heads": 16,
|
| 62 |
+
"num_conv_pos_embedding_groups": 16,
|
| 63 |
+
"num_conv_pos_embeddings": 128,
|
| 64 |
+
"num_feat_extract_layers": 7,
|
| 65 |
+
"num_hidden_layers": 24,
|
| 66 |
+
"pad_token_id": 0,
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.20.0.dev0",
|
| 69 |
+
"use_weighted_layer_sum": false,
|
| 70 |
+
"vocab_size": 32
|
| 71 |
+
}
|
ckpt/chinese-hubert-large/chinese-hubert-large_preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
ckpt/chinese-hubert-large/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:482c19cd60877832995d790ed10dd1203b1f8c86ed7a69b4bd27f470fc27ee43
|
| 3 |
+
size 1261871939
|
ckpt/gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
ckpt/stage1.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb07be497b8c3e6c32a0b6f960d958a1e03d3ee82982f6f1e7bc972077d3f36f
|
| 3 |
+
size 187780891
|
ckpt/stage2_audio_only_hubert.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b9c6c027ff8bfc2b9ab2531d68eb52d9c2e89bbde67cea271ff67a89c2a436e
|
| 3 |
+
size 342029570
|
ckpt/stage2_full_control_hubert.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf5783a946f69eaf5ec3baa31677838c7af8bbdd5986258e070326d962125a2b
|
| 3 |
+
size 359493190
|
ckpt/stage2_full_control_mfcc.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e6746d2e50def9cda65f96edf748ac158c5a8dc3743c86584381dd8e760a177
|
| 3 |
+
size 248849176
|
ckpt/stage2_pose_only_hubert.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0e18c9cb2c2f6c3a31aa498c4871cea3f70bed5d24165537b7e044784102ed0
|
| 3 |
+
size 347857390
|
ckpt/stage2_pose_only_mfcc.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0c27b3e4d3282f4a62ed1ab1e3bb983004d0b39238c66135973874101f1f459
|
| 3 |
+
size 237213440
|