Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +81 -0
- onnx/model.onnx +3 -0
- onnx/model.onnx_data +3 -0
- onnx/model_quantized.onnx +3 -0
- preprocessor_config.json +11 -0
- quantize_config.json +37 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
|
|
|
|
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
|
36 |
+
onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/w2v-bert-2.0",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_act": "relu",
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": false,
|
8 |
+
"apply_spec_augment": false,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2BertModel"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 768,
|
15 |
+
"codevector_dim": 768,
|
16 |
+
"conformer_conv_dropout": 0.1,
|
17 |
+
"contrastive_logits_temperature": 0.1,
|
18 |
+
"conv_depthwise_kernel_size": 31,
|
19 |
+
"ctc_loss_reduction": "sum",
|
20 |
+
"ctc_zero_infinity": false,
|
21 |
+
"diversity_loss_weight": 0.1,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"feat_proj_dropout": 0.0,
|
24 |
+
"feat_quantizer_dropout": 0.0,
|
25 |
+
"feature_projection_input_dim": 160,
|
26 |
+
"final_dropout": 0.1,
|
27 |
+
"hidden_act": "swish",
|
28 |
+
"hidden_dropout": 0.0,
|
29 |
+
"hidden_size": 1024,
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 4096,
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"layerdrop": 0.1,
|
34 |
+
"left_max_position_embeddings": 64,
|
35 |
+
"mask_feature_length": 10,
|
36 |
+
"mask_feature_min_masks": 0,
|
37 |
+
"mask_feature_prob": 0.0,
|
38 |
+
"mask_time_length": 10,
|
39 |
+
"mask_time_min_masks": 2,
|
40 |
+
"mask_time_prob": 0.05,
|
41 |
+
"max_source_positions": 5000,
|
42 |
+
"model_type": "wav2vec2-bert",
|
43 |
+
"num_adapter_layers": 1,
|
44 |
+
"num_attention_heads": 16,
|
45 |
+
"num_codevector_groups": 2,
|
46 |
+
"num_codevectors_per_group": 320,
|
47 |
+
"num_hidden_layers": 24,
|
48 |
+
"num_negatives": 100,
|
49 |
+
"output_hidden_size": 1024,
|
50 |
+
"pad_token_id": 0,
|
51 |
+
"position_embeddings_type": "relative_key",
|
52 |
+
"proj_codevector_dim": 768,
|
53 |
+
"right_max_position_embeddings": 8,
|
54 |
+
"rotary_embedding_base": 10000,
|
55 |
+
"tdnn_dilation": [
|
56 |
+
1,
|
57 |
+
2,
|
58 |
+
3,
|
59 |
+
1,
|
60 |
+
1
|
61 |
+
],
|
62 |
+
"tdnn_dim": [
|
63 |
+
512,
|
64 |
+
512,
|
65 |
+
512,
|
66 |
+
512,
|
67 |
+
1500
|
68 |
+
],
|
69 |
+
"tdnn_kernel": [
|
70 |
+
5,
|
71 |
+
3,
|
72 |
+
3,
|
73 |
+
1,
|
74 |
+
1
|
75 |
+
],
|
76 |
+
"transformers_version": "4.37.1",
|
77 |
+
"use_intermediate_ffn_before_adapter": false,
|
78 |
+
"use_weighted_layer_sum": false,
|
79 |
+
"vocab_size": null,
|
80 |
+
"xvector_output_dim": 512
|
81 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80094118ff71ce226aa69b71528d80b490dd3bb4cb19cc6fb6ee2b6d27994b95
|
3 |
+
size 988064
|
onnx/model.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2f2e435cacbbe867c95f228ff6ecb83bcb0805d02a86a445154dba74d1eb4b6
|
3 |
+
size 2321967104
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06af071a2ae91caa1350c3d4cea2a6d05aa2178818c7c60ad53dbbfeb636c174
|
3 |
+
size 585724351
|
preprocessor_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"feature_extractor_type": "SeamlessM4TFeatureExtractor",
|
3 |
+
"feature_size": 80,
|
4 |
+
"num_mel_bins": 80,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 1,
|
7 |
+
"processor_class": "Wav2Vec2BertProcessor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000,
|
10 |
+
"stride": 2
|
11 |
+
}
|
quantize_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"MatMul",
|
8 |
+
"Slice",
|
9 |
+
"Range",
|
10 |
+
"Shape",
|
11 |
+
"Transpose",
|
12 |
+
"ReduceMean",
|
13 |
+
"Cast",
|
14 |
+
"ConstantOfShape",
|
15 |
+
"Softmax",
|
16 |
+
"Div",
|
17 |
+
"Sigmoid",
|
18 |
+
"Clip",
|
19 |
+
"Gather",
|
20 |
+
"Einsum",
|
21 |
+
"Unsqueeze",
|
22 |
+
"Constant",
|
23 |
+
"Reshape",
|
24 |
+
"Sub",
|
25 |
+
"Split",
|
26 |
+
"Concat",
|
27 |
+
"Pow",
|
28 |
+
"Conv",
|
29 |
+
"Mul",
|
30 |
+
"Add",
|
31 |
+
"Pad",
|
32 |
+
"Sqrt"
|
33 |
+
],
|
34 |
+
"weight_type": "QUInt8"
|
35 |
+
}
|
36 |
+
}
|
37 |
+
}
|