Commit
•
730f180
1
Parent(s):
707e598
jonatasgrosman/exp_w2v2r_de_vp-100k_age_teens-5_sixties-5_s852
Browse files- .gitattributes +1 -0
- README.md +17 -0
- config.json +116 -0
- cv7_evaluation.json +396 -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 |
+
- de
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- automatic-speech-recognition
|
7 |
+
- de
|
8 |
+
datasets:
|
9 |
+
- mozilla-foundation/common_voice_7_0
|
10 |
+
---
|
11 |
+
# exp_w2v2r_de_vp-100k_age_teens-5_sixties-5_s852
|
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 (de)](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": 38,
|
115 |
+
"xvector_output_dim": 512
|
116 |
+
}
|
cv7_evaluation.json
ADDED
@@ -0,0 +1,396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"validation": [
|
3 |
+
{
|
4 |
+
"subset_type": "all",
|
5 |
+
"subset": "all",
|
6 |
+
"cer": 0.06299855493461792,
|
7 |
+
"wer": 0.24717299119278024
|
8 |
+
},
|
9 |
+
{
|
10 |
+
"subset_type": "age",
|
11 |
+
"subset": "",
|
12 |
+
"cer": 0.062066941963909925,
|
13 |
+
"wer": 0.2442990234033519
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"subset_type": "age",
|
17 |
+
"subset": "seventies",
|
18 |
+
"cer": 0.06162533758900074,
|
19 |
+
"wer": 0.26700680272108845
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"subset_type": "age",
|
23 |
+
"subset": "eighties",
|
24 |
+
"cer": 0.06199021207177814,
|
25 |
+
"wer": 0.2804878048780488
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"subset_type": "age",
|
29 |
+
"subset": "teens",
|
30 |
+
"cer": 0.06362695429536416,
|
31 |
+
"wer": 0.25344250093040566
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"subset_type": "age",
|
35 |
+
"subset": "twenties",
|
36 |
+
"cer": 0.06688495640337,
|
37 |
+
"wer": 0.26435916729370457
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"subset_type": "age",
|
41 |
+
"subset": "thirties",
|
42 |
+
"cer": 0.060090316106372305,
|
43 |
+
"wer": 0.2305372807017544
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"subset_type": "age",
|
47 |
+
"subset": "fifties",
|
48 |
+
"cer": 0.06980751243046325,
|
49 |
+
"wer": 0.272757923128793
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"subset_type": "age",
|
53 |
+
"subset": "fourties",
|
54 |
+
"cer": 0.08379281537176274,
|
55 |
+
"wer": 0.2978783592644979
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"subset_type": "age",
|
59 |
+
"subset": "sixties",
|
60 |
+
"cer": 0.06795612864977027,
|
61 |
+
"wer": 0.2697334030318871
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"subset_type": "gender",
|
65 |
+
"subset": "",
|
66 |
+
"cer": 0.062062737345387295,
|
67 |
+
"wer": 0.2442427774540005
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"subset_type": "gender",
|
71 |
+
"subset": "male",
|
72 |
+
"cer": 0.06747050747482966,
|
73 |
+
"wer": 0.2606863596872285
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"subset_type": "gender",
|
77 |
+
"subset": "other",
|
78 |
+
"cer": 0.09897292250233426,
|
79 |
+
"wer": 0.36585365853658536
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"subset_type": "gender",
|
83 |
+
"subset": "female",
|
84 |
+
"cer": 0.0643582988332706,
|
85 |
+
"wer": 0.2527216174183515
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"subset_type": "accent",
|
89 |
+
"subset": "",
|
90 |
+
"cer": 0.062627508934339,
|
91 |
+
"wer": 0.24613690968846175
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"subset_type": "accent",
|
95 |
+
"subset": "netherlands",
|
96 |
+
"cer": 0.08417508417508418,
|
97 |
+
"wer": 0.2391304347826087
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"subset_type": "accent",
|
101 |
+
"subset": "slovakia",
|
102 |
+
"cer": 0.06111111111111111,
|
103 |
+
"wer": 0.24561403508771928
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"subset_type": "accent",
|
107 |
+
"subset": "canada",
|
108 |
+
"cer": 0.10661764705882353,
|
109 |
+
"wer": 0.35
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"subset_type": "accent",
|
113 |
+
"subset": "germany",
|
114 |
+
"cer": 0.06279611402683172,
|
115 |
+
"wer": 0.24583424687568517
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"subset_type": "accent",
|
119 |
+
"subset": "switzerland",
|
120 |
+
"cer": 0.07387072622909907,
|
121 |
+
"wer": 0.30397236614853196
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"subset_type": "accent",
|
125 |
+
"subset": "czechia",
|
126 |
+
"cer": 0.059075342465753425,
|
127 |
+
"wer": 0.23636363636363636
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"subset_type": "accent",
|
131 |
+
"subset": "austria",
|
132 |
+
"cer": 0.06559551886792453,
|
133 |
+
"wer": 0.24619289340101522
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"subset_type": "accent",
|
137 |
+
"subset": "turkey",
|
138 |
+
"cer": 0.16216216216216217,
|
139 |
+
"wer": 0.5084745762711864
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"subset_type": "accent",
|
143 |
+
"subset": "other",
|
144 |
+
"cer": 0.10059880239520957,
|
145 |
+
"wer": 0.32
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"subset_type": "accent",
|
149 |
+
"subset": "russia",
|
150 |
+
"cer": 0.10665529010238908,
|
151 |
+
"wer": 0.3315508021390374
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"subset_type": "accent",
|
155 |
+
"subset": "luxembourg",
|
156 |
+
"cer": 0.09443099273607748,
|
157 |
+
"wer": 0.3305785123966942
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"subset_type": "accent",
|
161 |
+
"subset": "united_states",
|
162 |
+
"cer": 0.09090909090909091,
|
163 |
+
"wer": 0.36042402826855124
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"subset_type": "accent",
|
167 |
+
"subset": "belgium",
|
168 |
+
"cer": 0.04054054054054054,
|
169 |
+
"wer": 0.19230769230769232
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"subset_type": "accent",
|
173 |
+
"subset": "france",
|
174 |
+
"cer": 0.04054054054054054,
|
175 |
+
"wer": 0.20833333333333334
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"subset_type": "accent",
|
179 |
+
"subset": "united_kingdom",
|
180 |
+
"cer": 0.10233160621761658,
|
181 |
+
"wer": 0.37606837606837606
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"subset_type": "accent",
|
185 |
+
"subset": "poland",
|
186 |
+
"cer": 0.024390243902439025,
|
187 |
+
"wer": 0.09090909090909091
|
188 |
+
}
|
189 |
+
],
|
190 |
+
"test": [
|
191 |
+
{
|
192 |
+
"subset_type": "all",
|
193 |
+
"subset": "all",
|
194 |
+
"cer": 0.07226561522969502,
|
195 |
+
"wer": 0.2666488090332152
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"subset_type": "age",
|
199 |
+
"subset": "",
|
200 |
+
"cer": 0.07136148873233782,
|
201 |
+
"wer": 0.26447706281378147
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"subset_type": "age",
|
205 |
+
"subset": "seventies",
|
206 |
+
"cer": 0.09514515735545255,
|
207 |
+
"wer": 0.3299492385786802
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"subset_type": "age",
|
211 |
+
"subset": "eighties",
|
212 |
+
"cer": 0.14311926605504588,
|
213 |
+
"wer": 0.4246575342465753
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"subset_type": "age",
|
217 |
+
"subset": "teens",
|
218 |
+
"cer": 0.08261731658955718,
|
219 |
+
"wer": 0.2905811623246493
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"subset_type": "age",
|
223 |
+
"subset": "twenties",
|
224 |
+
"cer": 0.07688392658332538,
|
225 |
+
"wer": 0.28364657593432707
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"subset_type": "age",
|
229 |
+
"subset": "thirties",
|
230 |
+
"cer": 0.07130141050805679,
|
231 |
+
"wer": 0.2612530413625304
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"subset_type": "age",
|
235 |
+
"subset": "fifties",
|
236 |
+
"cer": 0.06597346719254213,
|
237 |
+
"wer": 0.2540942928039702
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"subset_type": "age",
|
241 |
+
"subset": "fourties",
|
242 |
+
"cer": 0.10026879530830007,
|
243 |
+
"wer": 0.3257617728531856
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"subset_type": "age",
|
247 |
+
"subset": "sixties",
|
248 |
+
"cer": 0.10279828993392927,
|
249 |
+
"wer": 0.32697547683923706
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"subset_type": "gender",
|
253 |
+
"subset": "",
|
254 |
+
"cer": 0.07147205676732221,
|
255 |
+
"wer": 0.26475320655255374
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"subset_type": "gender",
|
259 |
+
"subset": "male",
|
260 |
+
"cer": 0.07472279115756762,
|
261 |
+
"wer": 0.27224796293337594
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"subset_type": "gender",
|
265 |
+
"subset": "other",
|
266 |
+
"cer": 0.1245819397993311,
|
267 |
+
"wer": 0.2840909090909091
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"subset_type": "gender",
|
271 |
+
"subset": "female",
|
272 |
+
"cer": 0.09892837682387842,
|
273 |
+
"wer": 0.3396147403685092
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"subset_type": "accent",
|
277 |
+
"subset": "",
|
278 |
+
"cer": 0.07232917255612405,
|
279 |
+
"wer": 0.2670242998039603
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"subset_type": "accent",
|
283 |
+
"subset": "netherlands",
|
284 |
+
"cer": 0.07488653555219364,
|
285 |
+
"wer": 0.3005181347150259
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"subset_type": "accent",
|
289 |
+
"subset": "greece",
|
290 |
+
"cer": 0.08974358974358974,
|
291 |
+
"wer": 0.2222222222222222
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"subset_type": "accent",
|
295 |
+
"subset": "turkey",
|
296 |
+
"cer": 0.20430107526881722,
|
297 |
+
"wer": 0.5333333333333333
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"subset_type": "accent",
|
301 |
+
"subset": "russia",
|
302 |
+
"cer": 0.21548821548821548,
|
303 |
+
"wer": 0.5777777777777777
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"subset_type": "accent",
|
307 |
+
"subset": "luxembourg",
|
308 |
+
"cer": 0.045774647887323945,
|
309 |
+
"wer": 0.18421052631578946
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"subset_type": "accent",
|
313 |
+
"subset": "united_states",
|
314 |
+
"cer": 0.07073760580411124,
|
315 |
+
"wer": 0.24481327800829875
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"subset_type": "accent",
|
319 |
+
"subset": "bulgaria",
|
320 |
+
"cer": 0.0,
|
321 |
+
"wer": 0.0
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"subset_type": "accent",
|
325 |
+
"subset": "belgium",
|
326 |
+
"cer": 0.07614213197969544,
|
327 |
+
"wer": 0.38095238095238093
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"subset_type": "accent",
|
331 |
+
"subset": "poland",
|
332 |
+
"cer": 0.1354515050167224,
|
333 |
+
"wer": 0.42391304347826086
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"subset_type": "accent",
|
337 |
+
"subset": "germany",
|
338 |
+
"cer": 0.06734015650032439,
|
339 |
+
"wer": 0.2505859022895259
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"subset_type": "accent",
|
343 |
+
"subset": "france",
|
344 |
+
"cer": 0.09117361784675072,
|
345 |
+
"wer": 0.36666666666666664
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"subset_type": "accent",
|
349 |
+
"subset": "denmark",
|
350 |
+
"cer": 0.04411764705882353,
|
351 |
+
"wer": 0.2222222222222222
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"subset_type": "accent",
|
355 |
+
"subset": "switzerland",
|
356 |
+
"cer": 0.09316013801501928,
|
357 |
+
"wer": 0.3319327731092437
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"subset_type": "accent",
|
361 |
+
"subset": "czechia",
|
362 |
+
"cer": 0.21951219512195122,
|
363 |
+
"wer": 0.5849056603773585
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"subset_type": "accent",
|
367 |
+
"subset": "slovakia",
|
368 |
+
"cer": 0.03787878787878788,
|
369 |
+
"wer": 0.1896551724137931
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"subset_type": "accent",
|
373 |
+
"subset": "hungary",
|
374 |
+
"cer": 0.11282051282051282,
|
375 |
+
"wer": 0.5
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"subset_type": "accent",
|
379 |
+
"subset": "austria",
|
380 |
+
"cer": 0.07579429186860527,
|
381 |
+
"wer": 0.2723915050784857
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"subset_type": "accent",
|
385 |
+
"subset": "other",
|
386 |
+
"cer": 0.021739130434782608,
|
387 |
+
"wer": 0.07142857142857142
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"subset_type": "accent",
|
391 |
+
"subset": "united_kingdom",
|
392 |
+
"cer": 0.13636363636363635,
|
393 |
+
"wer": 0.43137254901960786
|
394 |
+
}
|
395 |
+
]
|
396 |
+
}
|
cv7_transcriptions.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23aad9b311be1e4be4ed38bfec96fd7c7dced34636a13ffabc9636a2a86bc418
|
3 |
+
size 137913985
|
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:cb28c8ef57c0fab808ca98ab4391a744fe426943807f92bc4934a3a4ef0cae6a
|
3 |
+
size 1262054513
|
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/tmp8z6ddmrq", "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, "ß": 33, "á": 34, "ä": 35, "ö": 36, "ü": 37}
|