Commit
•
8edd715
1
Parent(s):
e5535b5
jonatasgrosman/exp_w2v2r_es_vp-100k_age_teens-5_sixties-5_s169
Browse files- .gitattributes +1 -0
- README.md +17 -0
- config.json +116 -0
- cv7_evaluation.json +300 -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
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
cv7_transcriptions.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- es
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- automatic-speech-recognition
|
7 |
+
- es
|
8 |
+
datasets:
|
9 |
+
- mozilla-foundation/common_voice_7_0
|
10 |
+
---
|
11 |
+
# exp_w2v2r_es_vp-100k_age_teens-5_sixties-5_s169
|
12 |
+
|
13 |
+
Fine-tuned [facebook/wav2vec2-large-100k-voxpopuli](https://huggingface.co/facebook/wav2vec2-large-100k-voxpopuli) for speech recognition using the train split of [Common Voice 7.0 (es)](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 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-100k-voxpopuli",
|
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_channel_length": 10,
|
64 |
+
"mask_channel_min_space": 1,
|
65 |
+
"mask_channel_other": 0.0,
|
66 |
+
"mask_channel_prob": 0.0,
|
67 |
+
"mask_channel_selection": "static",
|
68 |
+
"mask_feature_length": 10,
|
69 |
+
"mask_feature_min_masks": 0,
|
70 |
+
"mask_feature_prob": 0.0,
|
71 |
+
"mask_time_length": 10,
|
72 |
+
"mask_time_min_masks": 2,
|
73 |
+
"mask_time_min_space": 1,
|
74 |
+
"mask_time_other": 0.0,
|
75 |
+
"mask_time_prob": 0.05,
|
76 |
+
"mask_time_selection": "static",
|
77 |
+
"model_type": "wav2vec2",
|
78 |
+
"num_adapter_layers": 3,
|
79 |
+
"num_attention_heads": 16,
|
80 |
+
"num_codevector_groups": 2,
|
81 |
+
"num_codevectors_per_group": 320,
|
82 |
+
"num_conv_pos_embedding_groups": 16,
|
83 |
+
"num_conv_pos_embeddings": 128,
|
84 |
+
"num_feat_extract_layers": 7,
|
85 |
+
"num_hidden_layers": 24,
|
86 |
+
"num_negatives": 100,
|
87 |
+
"output_hidden_size": 1024,
|
88 |
+
"pad_token_id": 0,
|
89 |
+
"proj_codevector_dim": 768,
|
90 |
+
"tdnn_dilation": [
|
91 |
+
1,
|
92 |
+
2,
|
93 |
+
3,
|
94 |
+
1,
|
95 |
+
1
|
96 |
+
],
|
97 |
+
"tdnn_dim": [
|
98 |
+
512,
|
99 |
+
512,
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
1500
|
103 |
+
],
|
104 |
+
"tdnn_kernel": [
|
105 |
+
5,
|
106 |
+
3,
|
107 |
+
3,
|
108 |
+
1,
|
109 |
+
1
|
110 |
+
],
|
111 |
+
"torch_dtype": "float32",
|
112 |
+
"transformers_version": "4.18.0",
|
113 |
+
"use_weighted_layer_sum": false,
|
114 |
+
"vocab_size": 41,
|
115 |
+
"xvector_output_dim": 512
|
116 |
+
}
|
cv7_evaluation.json
ADDED
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"validation": [
|
3 |
+
{
|
4 |
+
"subset_type": "all",
|
5 |
+
"subset": "all",
|
6 |
+
"cer": 0.053364698623269445,
|
7 |
+
"wer": 0.19008040771597196
|
8 |
+
},
|
9 |
+
{
|
10 |
+
"subset_type": "age",
|
11 |
+
"subset": "",
|
12 |
+
"cer": 0.05320985204920356,
|
13 |
+
"wer": 0.1895298727570995
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"subset_type": "age",
|
17 |
+
"subset": "thirties",
|
18 |
+
"cer": 0.0520073599503425,
|
19 |
+
"wer": 0.19241443108233117
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"subset_type": "age",
|
23 |
+
"subset": "sixties",
|
24 |
+
"cer": 0.07505191337881933,
|
25 |
+
"wer": 0.20735981308411214
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"subset_type": "age",
|
29 |
+
"subset": "seventies",
|
30 |
+
"cer": 0.056451612903225805,
|
31 |
+
"wer": 0.24528301886792453
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"subset_type": "age",
|
35 |
+
"subset": "fifties",
|
36 |
+
"cer": 0.05287494973864093,
|
37 |
+
"wer": 0.19462279293739967
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"subset_type": "age",
|
41 |
+
"subset": "twenties",
|
42 |
+
"cer": 0.05502227472987275,
|
43 |
+
"wer": 0.19370727045504668
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"subset_type": "age",
|
47 |
+
"subset": "teens",
|
48 |
+
"cer": 0.05280925970581143,
|
49 |
+
"wer": 0.1960897067280046
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"subset_type": "age",
|
53 |
+
"subset": "fourties",
|
54 |
+
"cer": 0.04746569588350602,
|
55 |
+
"wer": 0.17418677859391396
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"subset_type": "gender",
|
59 |
+
"subset": "",
|
60 |
+
"cer": 0.05313383866953275,
|
61 |
+
"wer": 0.18933566285292647
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"subset_type": "gender",
|
65 |
+
"subset": "male",
|
66 |
+
"cer": 0.05484450032078492,
|
67 |
+
"wer": 0.19307218412181798
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"subset_type": "gender",
|
71 |
+
"subset": "other",
|
72 |
+
"cer": 0.06642512077294686,
|
73 |
+
"wer": 0.24954792043399637
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"subset_type": "gender",
|
77 |
+
"subset": "female",
|
78 |
+
"cer": 0.05083558958080478,
|
79 |
+
"wer": 0.18698848661395479
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"subset_type": "accent",
|
83 |
+
"subset": "",
|
84 |
+
"cer": 0.0531167324205152,
|
85 |
+
"wer": 0.1895910189543315
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"subset_type": "accent",
|
89 |
+
"subset": "chileno",
|
90 |
+
"cer": 0.06204337237620318,
|
91 |
+
"wer": 0.21727210418094586
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"subset_type": "accent",
|
95 |
+
"subset": "nortepeninsular",
|
96 |
+
"cer": 0.05225019069412662,
|
97 |
+
"wer": 0.18319327731092436
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"subset_type": "accent",
|
101 |
+
"subset": "canario",
|
102 |
+
"cer": 0.05062362435803375,
|
103 |
+
"wer": 0.19724770642201836
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"subset_type": "accent",
|
107 |
+
"subset": "surpeninsular",
|
108 |
+
"cer": 0.0636060977746627,
|
109 |
+
"wer": 0.22361546499477533
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"subset_type": "accent",
|
113 |
+
"subset": "caribe",
|
114 |
+
"cer": 0.051010213143872114,
|
115 |
+
"wer": 0.1810892081523555
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"subset_type": "accent",
|
119 |
+
"subset": "mexicano",
|
120 |
+
"cer": 0.051596370939815776,
|
121 |
+
"wer": 0.1878369039391845
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"subset_type": "accent",
|
125 |
+
"subset": "rioplatense",
|
126 |
+
"cer": 0.05117549275706483,
|
127 |
+
"wer": 0.1840974212034384
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"subset_type": "accent",
|
131 |
+
"subset": "andino",
|
132 |
+
"cer": 0.05324268581468184,
|
133 |
+
"wer": 0.19149420059131225
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"subset_type": "accent",
|
137 |
+
"subset": "centrosurpeninsular",
|
138 |
+
"cer": 0.06990151333173192,
|
139 |
+
"wer": 0.21508903467666354
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"subset_type": "accent",
|
143 |
+
"subset": "americacentral",
|
144 |
+
"cer": 0.05543364182806984,
|
145 |
+
"wer": 0.1905311778290993
|
146 |
+
}
|
147 |
+
],
|
148 |
+
"test": [
|
149 |
+
{
|
150 |
+
"subset_type": "all",
|
151 |
+
"subset": "all",
|
152 |
+
"cer": 0.06105257586917116,
|
153 |
+
"wer": 0.20685918908026613
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"subset_type": "age",
|
157 |
+
"subset": "",
|
158 |
+
"cer": 0.0614137077394763,
|
159 |
+
"wer": 0.2074953445065177
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"subset_type": "age",
|
163 |
+
"subset": "thirties",
|
164 |
+
"cer": 0.057761039160677916,
|
165 |
+
"wer": 0.2052873563218391
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"subset_type": "age",
|
169 |
+
"subset": "sixties",
|
170 |
+
"cer": 0.05557714729887291,
|
171 |
+
"wer": 0.18569780853517878
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"subset_type": "age",
|
175 |
+
"subset": "seventies",
|
176 |
+
"cer": 0.15384615384615385,
|
177 |
+
"wer": 0.3780487804878049
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"subset_type": "age",
|
181 |
+
"subset": "fifties",
|
182 |
+
"cer": 0.05619125459746629,
|
183 |
+
"wer": 0.1824788050060557
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"subset_type": "age",
|
187 |
+
"subset": "twenties",
|
188 |
+
"cer": 0.05897564398115666,
|
189 |
+
"wer": 0.2015838732901368
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"subset_type": "age",
|
193 |
+
"subset": "eighties",
|
194 |
+
"cer": 0.06711409395973154,
|
195 |
+
"wer": 0.3333333333333333
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"subset_type": "age",
|
199 |
+
"subset": "teens",
|
200 |
+
"cer": 0.07002763361865606,
|
201 |
+
"wer": 0.24786324786324787
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"subset_type": "age",
|
205 |
+
"subset": "fourties",
|
206 |
+
"cer": 0.05383925137802846,
|
207 |
+
"wer": 0.18867438867438868
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"subset_type": "gender",
|
211 |
+
"subset": "",
|
212 |
+
"cer": 0.06145848547162763,
|
213 |
+
"wer": 0.20765268579838117
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"subset_type": "gender",
|
217 |
+
"subset": "male",
|
218 |
+
"cer": 0.058473372437984984,
|
219 |
+
"wer": 0.20035850584017578
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"subset_type": "gender",
|
223 |
+
"subset": "other",
|
224 |
+
"cer": 0.10473457675753228,
|
225 |
+
"wer": 0.3
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"subset_type": "gender",
|
229 |
+
"subset": "female",
|
230 |
+
"cer": 0.05724652997956739,
|
231 |
+
"wer": 0.20443974630021142
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"subset_type": "accent",
|
235 |
+
"subset": "",
|
236 |
+
"cer": 0.06170167584798599,
|
237 |
+
"wer": 0.2084945798956676
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"subset_type": "accent",
|
241 |
+
"subset": "chileno",
|
242 |
+
"cer": 0.04688463911165947,
|
243 |
+
"wer": 0.17017383348581885
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"subset_type": "accent",
|
247 |
+
"subset": "nortepeninsular",
|
248 |
+
"cer": 0.051231831769920626,
|
249 |
+
"wer": 0.172434729811779
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"subset_type": "accent",
|
253 |
+
"subset": "canario",
|
254 |
+
"cer": 0.06172839506172839,
|
255 |
+
"wer": 0.21656050955414013
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"subset_type": "accent",
|
259 |
+
"subset": "surpeninsular",
|
260 |
+
"cer": 0.053134182174338886,
|
261 |
+
"wer": 0.19703703703703704
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"subset_type": "accent",
|
265 |
+
"subset": "caribe",
|
266 |
+
"cer": 0.06825813987443423,
|
267 |
+
"wer": 0.2172797262617622
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"subset_type": "accent",
|
271 |
+
"subset": "mexicano",
|
272 |
+
"cer": 0.05392694063926941,
|
273 |
+
"wer": 0.18858421936205932
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"subset_type": "accent",
|
277 |
+
"subset": "rioplatense",
|
278 |
+
"cer": 0.07297979797979798,
|
279 |
+
"wer": 0.2296793437733035
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"subset_type": "accent",
|
283 |
+
"subset": "andino",
|
284 |
+
"cer": 0.0510572173816527,
|
285 |
+
"wer": 0.18877380554627465
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"subset_type": "accent",
|
289 |
+
"subset": "centrosurpeninsular",
|
290 |
+
"cer": 0.044894232232536906,
|
291 |
+
"wer": 0.16964285714285715
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"subset_type": "accent",
|
295 |
+
"subset": "americacentral",
|
296 |
+
"cer": 0.053480141565080616,
|
297 |
+
"wer": 0.19670846394984326
|
298 |
+
}
|
299 |
+
]
|
300 |
+
}
|
cv7_transcriptions.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6f32206f64d19306c00d1feff723e9df11840f4da7d04eceda8849a4f4bd518
|
3 |
+
size 125148345
|
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 sha256:50d42571e8eade6420bf0f58efe3903598e3e99762eba97f51805cc10c60af54
|
3 |
+
size 1262066801
|
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/tmpc0sm8n1n", "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, "á": 33, "é": 34, "í": 35, "ñ": 36, "ó": 37, "ö": 38, "ú": 39, "ü": 40}
|