jonatasgrosman
commited on
Commit
•
6f0241d
1
Parent(s):
80e50ba
jonatasgrosman/exp_w2v2r_en_xls-r_accent_us-8_england-2_s884
Browse files- .gitattributes +1 -0
- README.md +17 -0
- config.json +108 -0
- cv7_evaluation.json +390 -0
- cv7_transcriptions.json +3 -0
- preprocessor_config.json +10 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
.gitattributes
CHANGED
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
32 |
+
cv7_transcriptions.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- automatic-speech-recognition
|
7 |
+
- en
|
8 |
+
datasets:
|
9 |
+
- mozilla-foundation/common_voice_7_0
|
10 |
+
---
|
11 |
+
# exp_w2v2r_en_xls-r_accent_us-8_england-2_s884
|
12 |
+
|
13 |
+
Fine-tuned [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) for speech recognition using the train split of [Common Voice 7.0 (en)](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0).
|
14 |
+
When using this model, make sure that your speech input is sampled at 16kHz.
|
15 |
+
|
16 |
+
This model has been fine-tuned by the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) tool.
|
17 |
+
|
config.json
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
3 |
+
"activation_dropout": 0.05,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.05,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 768,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": true,
|
17 |
+
"conv_dim": [
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512
|
25 |
+
],
|
26 |
+
"conv_kernel": [
|
27 |
+
10,
|
28 |
+
3,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
2,
|
33 |
+
2
|
34 |
+
],
|
35 |
+
"conv_stride": [
|
36 |
+
5,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2
|
43 |
+
],
|
44 |
+
"ctc_loss_reduction": "mean",
|
45 |
+
"ctc_zero_infinity": false,
|
46 |
+
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": true,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "layer",
|
52 |
+
"feat_proj_dropout": 0.05,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.05,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.05,
|
58 |
+
"hidden_size": 1024,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 4096,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.05,
|
63 |
+
"mask_feature_length": 10,
|
64 |
+
"mask_feature_min_masks": 0,
|
65 |
+
"mask_feature_prob": 0.0,
|
66 |
+
"mask_time_length": 10,
|
67 |
+
"mask_time_min_masks": 2,
|
68 |
+
"mask_time_prob": 0.05,
|
69 |
+
"model_type": "wav2vec2",
|
70 |
+
"num_adapter_layers": 3,
|
71 |
+
"num_attention_heads": 16,
|
72 |
+
"num_codevector_groups": 2,
|
73 |
+
"num_codevectors_per_group": 320,
|
74 |
+
"num_conv_pos_embedding_groups": 16,
|
75 |
+
"num_conv_pos_embeddings": 128,
|
76 |
+
"num_feat_extract_layers": 7,
|
77 |
+
"num_hidden_layers": 24,
|
78 |
+
"num_negatives": 100,
|
79 |
+
"output_hidden_size": 1024,
|
80 |
+
"pad_token_id": 0,
|
81 |
+
"proj_codevector_dim": 768,
|
82 |
+
"tdnn_dilation": [
|
83 |
+
1,
|
84 |
+
2,
|
85 |
+
3,
|
86 |
+
1,
|
87 |
+
1
|
88 |
+
],
|
89 |
+
"tdnn_dim": [
|
90 |
+
512,
|
91 |
+
512,
|
92 |
+
512,
|
93 |
+
512,
|
94 |
+
1500
|
95 |
+
],
|
96 |
+
"tdnn_kernel": [
|
97 |
+
5,
|
98 |
+
3,
|
99 |
+
3,
|
100 |
+
1,
|
101 |
+
1
|
102 |
+
],
|
103 |
+
"torch_dtype": "float32",
|
104 |
+
"transformers_version": "4.18.0",
|
105 |
+
"use_weighted_layer_sum": false,
|
106 |
+
"vocab_size": 33,
|
107 |
+
"xvector_output_dim": 512
|
108 |
+
}
|
cv7_evaluation.json
ADDED
@@ -0,0 +1,390 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"validation": [
|
3 |
+
{
|
4 |
+
"subset_type": "all",
|
5 |
+
"subset": "all",
|
6 |
+
"cer": 0.10643609558859864,
|
7 |
+
"wer": 0.2964366091522881
|
8 |
+
},
|
9 |
+
{
|
10 |
+
"subset_type": "age",
|
11 |
+
"subset": "",
|
12 |
+
"cer": 0.10500801122726357,
|
13 |
+
"wer": 0.2930402657013845
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"subset_type": "age",
|
17 |
+
"subset": "sixties",
|
18 |
+
"cer": 0.08090614886731391,
|
19 |
+
"wer": 0.23776223776223776
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"subset_type": "age",
|
23 |
+
"subset": "seventies",
|
24 |
+
"cer": 0.09654300168634064,
|
25 |
+
"wer": 0.26555023923444976
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"subset_type": "age",
|
29 |
+
"subset": "fourties",
|
30 |
+
"cer": 0.09489281210592686,
|
31 |
+
"wer": 0.2703296703296703
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"subset_type": "age",
|
35 |
+
"subset": "thirties",
|
36 |
+
"cer": 0.10917332997544545,
|
37 |
+
"wer": 0.3072564430634253
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"subset_type": "age",
|
41 |
+
"subset": "fifties",
|
42 |
+
"cer": 0.07973556395035078,
|
43 |
+
"wer": 0.25533596837944667
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"subset_type": "age",
|
47 |
+
"subset": "teens",
|
48 |
+
"cer": 0.11194483877509633,
|
49 |
+
"wer": 0.31040564373897706
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"subset_type": "age",
|
53 |
+
"subset": "twenties",
|
54 |
+
"cer": 0.12803937412767208,
|
55 |
+
"wer": 0.34310774787170006
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"subset_type": "age",
|
59 |
+
"subset": "nineties",
|
60 |
+
"cer": 0.038461538461538464,
|
61 |
+
"wer": 0.14285714285714285
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"subset_type": "age",
|
65 |
+
"subset": "eighties",
|
66 |
+
"cer": 0.11827956989247312,
|
67 |
+
"wer": 0.3269230769230769
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"subset_type": "gender",
|
71 |
+
"subset": "",
|
72 |
+
"cer": 0.10508889858121456,
|
73 |
+
"wer": 0.2931882467963788
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"subset_type": "gender",
|
77 |
+
"subset": "female",
|
78 |
+
"cer": 0.1096746306193021,
|
79 |
+
"wer": 0.3037511436413541
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"subset_type": "gender",
|
83 |
+
"subset": "male",
|
84 |
+
"cer": 0.11438625944340415,
|
85 |
+
"wer": 0.31554197037385373
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"subset_type": "gender",
|
89 |
+
"subset": "other",
|
90 |
+
"cer": 0.09792284866468842,
|
91 |
+
"wer": 0.2874251497005988
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"subset_type": "accent",
|
95 |
+
"subset": "",
|
96 |
+
"cer": 0.1072706878581968,
|
97 |
+
"wer": 0.29779980539163187
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"subset_type": "accent",
|
101 |
+
"subset": "african",
|
102 |
+
"cer": 0.13177159590043924,
|
103 |
+
"wer": 0.3498542274052478
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"subset_type": "accent",
|
107 |
+
"subset": "bermuda",
|
108 |
+
"cer": 0.06172839506172839,
|
109 |
+
"wer": 0.125
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"subset_type": "accent",
|
113 |
+
"subset": "scotland",
|
114 |
+
"cer": 0.0800711743772242,
|
115 |
+
"wer": 0.25
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"subset_type": "accent",
|
119 |
+
"subset": "malaysia",
|
120 |
+
"cer": 0.1564102564102564,
|
121 |
+
"wer": 0.3611111111111111
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"subset_type": "accent",
|
125 |
+
"subset": "wales",
|
126 |
+
"cer": 0.06666666666666667,
|
127 |
+
"wer": 0.2638888888888889
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"subset_type": "accent",
|
131 |
+
"subset": "canada",
|
132 |
+
"cer": 0.07026476578411406,
|
133 |
+
"wer": 0.22541966426858512
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"subset_type": "accent",
|
137 |
+
"subset": "us",
|
138 |
+
"cer": 0.08369491852280397,
|
139 |
+
"wer": 0.2536084799278304
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"subset_type": "accent",
|
143 |
+
"subset": "hongkong",
|
144 |
+
"cer": 0.08103130755064457,
|
145 |
+
"wer": 0.2608695652173913
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"subset_type": "accent",
|
149 |
+
"subset": "newzealand",
|
150 |
+
"cer": 0.059113300492610835,
|
151 |
+
"wer": 0.15
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"subset_type": "accent",
|
155 |
+
"subset": "ireland",
|
156 |
+
"cer": 0.11857707509881422,
|
157 |
+
"wer": 0.33070866141732286
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"subset_type": "accent",
|
161 |
+
"subset": "southatlandtic",
|
162 |
+
"cer": 0.1043956043956044,
|
163 |
+
"wer": 0.2727272727272727
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"subset_type": "accent",
|
167 |
+
"subset": "other",
|
168 |
+
"cer": 0.10780669144981413,
|
169 |
+
"wer": 0.34
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"subset_type": "accent",
|
173 |
+
"subset": "indian",
|
174 |
+
"cer": 0.14959860024701524,
|
175 |
+
"wer": 0.38755261575466027
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"subset_type": "accent",
|
179 |
+
"subset": "england",
|
180 |
+
"cer": 0.0870834764685675,
|
181 |
+
"wer": 0.2586891757696127
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"subset_type": "accent",
|
185 |
+
"subset": "australia",
|
186 |
+
"cer": 0.07140172867343104,
|
187 |
+
"wer": 0.20361990950226244
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"subset_type": "accent",
|
191 |
+
"subset": "singapore",
|
192 |
+
"cer": 0.16132723112128147,
|
193 |
+
"wer": 0.3246753246753247
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"subset_type": "accent",
|
197 |
+
"subset": "philippines",
|
198 |
+
"cer": 0.1552647233789411,
|
199 |
+
"wer": 0.43252595155709345
|
200 |
+
}
|
201 |
+
],
|
202 |
+
"test": [
|
203 |
+
{
|
204 |
+
"subset_type": "all",
|
205 |
+
"subset": "all",
|
206 |
+
"cer": 0.13900100702589743,
|
207 |
+
"wer": 0.34407899038775913
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"subset_type": "age",
|
211 |
+
"subset": "",
|
212 |
+
"cer": 0.1374377341122707,
|
213 |
+
"wer": 0.3406865914605853
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"subset_type": "age",
|
217 |
+
"subset": "seventies",
|
218 |
+
"cer": 0.14707655213984328,
|
219 |
+
"wer": 0.33221476510067116
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"subset_type": "age",
|
223 |
+
"subset": "sixties",
|
224 |
+
"cer": 0.13913392141138733,
|
225 |
+
"wer": 0.28193832599118945
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"subset_type": "age",
|
229 |
+
"subset": "fourties",
|
230 |
+
"cer": 0.1369284084185614,
|
231 |
+
"wer": 0.3242481203007519
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"subset_type": "age",
|
235 |
+
"subset": "thirties",
|
236 |
+
"cer": 0.13230358833146888,
|
237 |
+
"wer": 0.34219512195121954
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"subset_type": "age",
|
241 |
+
"subset": "fifties",
|
242 |
+
"cer": 0.19882839421088905,
|
243 |
+
"wer": 0.4013605442176871
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"subset_type": "age",
|
247 |
+
"subset": "teens",
|
248 |
+
"cer": 0.14963351409331982,
|
249 |
+
"wer": 0.381211708645337
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"subset_type": "age",
|
253 |
+
"subset": "twenties",
|
254 |
+
"cer": 0.1521847070506455,
|
255 |
+
"wer": 0.37810803086596173
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"subset_type": "age",
|
259 |
+
"subset": "eighties",
|
260 |
+
"cer": 0.11428571428571428,
|
261 |
+
"wer": 0.44
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"subset_type": "gender",
|
265 |
+
"subset": "",
|
266 |
+
"cer": 0.13739539188266792,
|
267 |
+
"wer": 0.34059750747074435
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"subset_type": "gender",
|
271 |
+
"subset": "female",
|
272 |
+
"cer": 0.14389277146135393,
|
273 |
+
"wer": 0.3654475170978293
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"subset_type": "gender",
|
277 |
+
"subset": "male",
|
278 |
+
"cer": 0.1488499571137029,
|
279 |
+
"wer": 0.3653424734505816
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"subset_type": "gender",
|
283 |
+
"subset": "other",
|
284 |
+
"cer": 0.20166320166320167,
|
285 |
+
"wer": 0.3735408560311284
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"subset_type": "accent",
|
289 |
+
"subset": "",
|
290 |
+
"cer": 0.1394431968151894,
|
291 |
+
"wer": 0.3448821844457559
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"subset_type": "accent",
|
295 |
+
"subset": "african",
|
296 |
+
"cer": 0.1675025075225677,
|
297 |
+
"wer": 0.4046242774566474
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"subset_type": "accent",
|
301 |
+
"subset": "bermuda",
|
302 |
+
"cer": 0.14157303370786517,
|
303 |
+
"wer": 0.32142857142857145
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"subset_type": "accent",
|
307 |
+
"subset": "scotland",
|
308 |
+
"cer": 0.10518934081346423,
|
309 |
+
"wer": 0.24822695035460993
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"subset_type": "accent",
|
313 |
+
"subset": "malaysia",
|
314 |
+
"cer": 0.1019036954087346,
|
315 |
+
"wer": 0.27388535031847133
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"subset_type": "accent",
|
319 |
+
"subset": "wales",
|
320 |
+
"cer": 0.15753424657534246,
|
321 |
+
"wer": 0.375
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"subset_type": "accent",
|
325 |
+
"subset": "canada",
|
326 |
+
"cer": 0.16360476663356505,
|
327 |
+
"wer": 0.31179775280898875
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"subset_type": "accent",
|
331 |
+
"subset": "us",
|
332 |
+
"cer": 0.11796841194288187,
|
333 |
+
"wer": 0.30674002751031637
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"subset_type": "accent",
|
337 |
+
"subset": "hongkong",
|
338 |
+
"cer": 0.23265895953757226,
|
339 |
+
"wer": 0.5083333333333333
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"subset_type": "accent",
|
343 |
+
"subset": "newzealand",
|
344 |
+
"cer": 0.07951482479784366,
|
345 |
+
"wer": 0.27941176470588236
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"subset_type": "accent",
|
349 |
+
"subset": "ireland",
|
350 |
+
"cer": 0.1378809869375907,
|
351 |
+
"wer": 0.31645569620253167
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"subset_type": "accent",
|
355 |
+
"subset": "other",
|
356 |
+
"cer": 0.1996879875195008,
|
357 |
+
"wer": 0.38996138996138996
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"subset_type": "accent",
|
361 |
+
"subset": "indian",
|
362 |
+
"cer": 0.1718131868131868,
|
363 |
+
"wer": 0.410933081998115
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"subset_type": "accent",
|
367 |
+
"subset": "england",
|
368 |
+
"cer": 0.11246170570214448,
|
369 |
+
"wer": 0.31712832108535893
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"subset_type": "accent",
|
373 |
+
"subset": "australia",
|
374 |
+
"cer": 0.11188436830835118,
|
375 |
+
"wer": 0.3248407643312102
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"subset_type": "accent",
|
379 |
+
"subset": "singapore",
|
380 |
+
"cer": 0.11764705882352941,
|
381 |
+
"wer": 0.3333333333333333
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"subset_type": "accent",
|
385 |
+
"subset": "philippines",
|
386 |
+
"cer": 0.11872909698996656,
|
387 |
+
"wer": 0.30303030303030304
|
388 |
+
}
|
389 |
+
]
|
390 |
+
}
|
cv7_transcriptions.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be068de18f874104ec10107e13a5d91544cc4e248ee0e5e30dc303968508b5be
|
3 |
+
size 123131166
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0ae04809c32956a63f052cefa2c859c124d888d493257efca63ed7a0ad6153a
|
3 |
+
size 1262034033
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "/tmp/tmps_60s4kf", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "'": 5, "-": 6, "a": 7, "b": 8, "c": 9, "d": 10, "e": 11, "f": 12, "g": 13, "h": 14, "i": 15, "j": 16, "k": 17, "l": 18, "m": 19, "n": 20, "o": 21, "p": 22, "q": 23, "r": 24, "s": 25, "t": 26, "u": 27, "v": 28, "w": 29, "x": 30, "y": 31, "z": 32}
|