Hugging Face's logo

qanastek
/
51-languages-classifier

Text Classification
Transformers
PyTorch
Transformers
multi-class-classification
Inference Endpoints
Model card Files Community
3
qanastek commited on
Commit
21e0ca7
•
1 Parent(s): d445fef

First update

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. README.md +214 -1
  3. config.json +3 -0
  4. optimizer.pt +3 -0
  5. pytorch_model.bin +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. sentencepiece.bpe.model +3 -0
  9. special_tokens_map.json +3 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +3 -0
  12. trainer_state.json +3 -0
  13. training_args.bin +3 -0
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,216 @@
1
  ---
2
- license: cc-by-sa-4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - Transformers
4
+ - text-classification
5
+ - multi-class-classification
6
+ languages:
7
+ - af-ZA
8
+ - am-ET
9
+ - ar-SA
10
+ - az-AZ
11
+ - bn-BD
12
+ - cy-GB
13
+ - da-DK
14
+ - de-DE
15
+ - el-GR
16
+ - en-US
17
+ - es-ES
18
+ - fa-IR
19
+ - fi-FI
20
+ - fr-FR
21
+ - he-IL
22
+ - hi-IN
23
+ - hu-HU
24
+ - hy-AM
25
+ - id-ID
26
+ - is-IS
27
+ - it-IT
28
+ - ja-JP
29
+ - jv-ID
30
+ - ka-GE
31
+ - km-KH
32
+ - kn-IN
33
+ - ko-KR
34
+ - lv-LV
35
+ - ml-IN
36
+ - mn-MN
37
+ - ms-MY
38
+ - my-MM
39
+ - nb-NO
40
+ - nl-NL
41
+ - pl-PL
42
+ - pt-PT
43
+ - ro-RO
44
+ - ru-RU
45
+ - sl-SL
46
+ - sq-AL
47
+ - sv-SE
48
+ - sw-KE
49
+ - ta-IN
50
+ - te-IN
51
+ - th-TH
52
+ - tl-PH
53
+ - tr-TR
54
+ - ur-PK
55
+ - vi-VN
56
+ - zh-CN
57
+ - zh-TW
58
+ multilinguality:
59
+ - af-ZA
60
+ - am-ET
61
+ - ar-SA
62
+ - az-AZ
63
+ - bn-BD
64
+ - cy-GB
65
+ - da-DK
66
+ - de-DE
67
+ - el-GR
68
+ - en-US
69
+ - es-ES
70
+ - fa-IR
71
+ - fi-FI
72
+ - fr-FR
73
+ - he-IL
74
+ - hi-IN
75
+ - hu-HU
76
+ - hy-AM
77
+ - id-ID
78
+ - is-IS
79
+ - it-IT
80
+ - ja-JP
81
+ - jv-ID
82
+ - ka-GE
83
+ - km-KH
84
+ - kn-IN
85
+ - ko-KR
86
+ - lv-LV
87
+ - ml-IN
88
+ - mn-MN
89
+ - ms-MY
90
+ - my-MM
91
+ - nb-NO
92
+ - nl-NL
93
+ - pl-PL
94
+ - pt-PT
95
+ - ro-RO
96
+ - ru-RU
97
+ - sl-SL
98
+ - sq-AL
99
+ - sv-SE
100
+ - sw-KE
101
+ - ta-IN
102
+ - te-IN
103
+ - th-TH
104
+ - tl-PH
105
+ - tr-TR
106
+ - ur-PK
107
+ - vi-VN
108
+ - zh-CN
109
+ - zh-TW
110
+ datasets:
111
+ - qanastek/MASSIVE
112
+ widget:
113
+ - text: "wake me up at five am this week"
114
+ - text: "je veux écouter la chanson de jacques brel encore une fois"
115
+ - text: "quiero escuchar la canción de arijit singh una vez más"
116
+ - text: "olly onde é que á um parque por perto onde eu possa correr"
117
+ - text: "פרק הבא בפודקאסט בבקשה"
118
+ - text: "亚马逊股价"
119
+ - text: "найди билет на поезд в санкт-петербург"
120
+ license: cc-by-4.0
121
  ---
122
+
123
+ **People Involved**
124
+
125
+ * [LABRAK Yanis](https://www.linkedin.com/in/yanis-labrak-8a7412145/) (1)
126
+
127
+ **Affiliations**
128
+
129
+ 1. [LIA, NLP team](https://lia.univ-avignon.fr/), Avignon University, Avignon, France.
130
+
131
+ ## Demo: How to use in HuggingFace Transformers Pipeline
132
+
133
+ Requires [transformers](https://pypi.org/project/transformers/): ```pip install transformers```
134
+
135
+ ```python
136
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification, TextClassificationPipeline
137
+ model_name = 'qanastek/51-languages-classifier'
138
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
139
+ model = AutoModelForSequenceClassification.from_pretrained(model_name)
140
+ classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer)
141
+ res = classifier("פרק הבא בפודקאסט בבקשה")
142
+ print(res)
143
+ ```
144
+
145
+ Outputs:
146
+
147
+ ```python
148
+ [{'label': 'fr-FR', 'score': 0.9998375177383423}]
149
+ ```
150
+
151
+ ## Training data
152
+
153
+ [MASSIVE](https://huggingface.co/datasets/qanastek/MASSIVE) is a parallel dataset of > 1M utterances across 51 languages with annotations for the Natural Language Understanding tasks of intent prediction and slot annotation. Utterances span 60 intents and include 55 slot types. MASSIVE was created by localizing the SLURP dataset, composed of general Intelligent Voice Assistant single-shot interactions.
154
+
155
+
156
+ ## Evaluation results
157
+
158
+ ```plain
159
+ precision recall f1-score support
160
+
161
+ af-ZA 0.9821 0.9805 0.9813 2974
162
+ am-ET 1.0000 1.0000 1.0000 2974
163
+ ar-SA 0.9809 0.9822 0.9815 2974
164
+ az-AZ 0.9946 0.9845 0.9895 2974
165
+ bn-BD 0.9997 0.9990 0.9993 2974
166
+ cy-GB 0.9970 0.9929 0.9949 2974
167
+ da-DK 0.9575 0.9617 0.9596 2974
168
+ de-DE 0.9906 0.9909 0.9908 2974
169
+ el-GR 0.9997 0.9973 0.9985 2974
170
+ en-US 0.9712 0.9866 0.9788 2974
171
+ es-ES 0.9825 0.9842 0.9834 2974
172
+ fa-IR 0.9940 0.9973 0.9956 2974
173
+ fi-FI 0.9943 0.9946 0.9945 2974
174
+ fr-FR 0.9963 0.9923 0.9943 2974
175
+ he-IL 1.0000 0.9997 0.9998 2974
176
+ hi-IN 1.0000 0.9980 0.9990 2974
177
+ hu-HU 0.9983 0.9950 0.9966 2974
178
+ hy-AM 1.0000 0.9993 0.9997 2974
179
+ id-ID 0.9319 0.9291 0.9305 2974
180
+ is-IS 0.9966 0.9943 0.9955 2974
181
+ it-IT 0.9698 0.9926 0.9811 2974
182
+ ja-JP 0.9987 0.9963 0.9975 2974
183
+ jv-ID 0.9628 0.9744 0.9686 2974
184
+ ka-GE 0.9993 0.9997 0.9995 2974
185
+ km-KH 0.9867 0.9963 0.9915 2974
186
+ kn-IN 1.0000 0.9993 0.9997 2974
187
+ ko-KR 0.9917 0.9997 0.9956 2974
188
+ lv-LV 0.9990 0.9950 0.9970 2974
189
+ ml-IN 0.9997 0.9997 0.9997 2974
190
+ mn-MN 0.9987 0.9966 0.9976 2974
191
+ ms-MY 0.9359 0.9418 0.9388 2974
192
+ my-MM 1.0000 0.9993 0.9997 2974
193
+ nb-NO 0.9600 0.9533 0.9566 2974
194
+ nl-NL 0.9850 0.9748 0.9799 2974
195
+ pl-PL 0.9946 0.9923 0.9934 2974
196
+ pt-PT 0.9885 0.9798 0.9841 2974
197
+ ro-RO 0.9919 0.9916 0.9918 2974
198
+ ru-RU 0.9976 0.9983 0.9980 2974
199
+ sl-SL 0.9956 0.9939 0.9948 2974
200
+ sq-AL 0.9936 0.9896 0.9916 2974
201
+ sv-SE 0.9902 0.9842 0.9872 2974
202
+ sw-KE 0.9867 0.9953 0.9910 2974
203
+ ta-IN 1.0000 1.0000 1.0000 2974
204
+ te-IN 1.0000 0.9997 0.9998 2974
205
+ th-TH 1.0000 0.9983 0.9992 2974
206
+ tl-PH 0.9929 0.9899 0.9914 2974
207
+ tr-TR 0.9869 0.9872 0.9871 2974
208
+ ur-PK 0.9983 0.9929 0.9956 2974
209
+ vi-VN 0.9993 0.9973 0.9983 2974
210
+ zh-CN 0.9812 0.9832 0.9822 2974
211
+ zh-TW 0.9832 0.9815 0.9823 2974
212
+
213
+ accuracy 0.9889 151674
214
+ macro avg 0.9889 0.9889 0.9889 151674
215
+ weighted avg 0.9889 0.9889 0.9889 151674
216
+ ```
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5e717ed1222ea2d1da259d79d0f844cbc139a1e5ba25387bc8c2c640b20668
3
+ size 2912
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14503cad0cf8ef115210c825e30ac3aa6ef6b6af57f8b14b0df2c13fe9e8b270
3
+ size 2224779869
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802a39a0e52e2ed6e1b90ce6ad7552f77c4e80370246c0e2d9473329ea256263
3
+ size 1112403117
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027717d8103c9237aa4ea05699c9898f259c407c504aacd1fd633b59abaf9ea8
3
+ size 15523
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c713a6c8e565ba2920aeb9096491484c3dd4706e7096d1811dfb74dfceb2a4e2
3
+ size 623
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378eb3bf733eb16e65792d7e3fda5b8a4631387ca04d2015199c4d4f22ae554d
3
+ size 239
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
+ size 17082758
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a29b4422dd3e2b3311e0b5026f27f884f4c0b0ca566e8cd598025cf873f493d
3
+ size 398
trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c42750649f65dbeebf47c794bfc8b6cb0896d2753e51afb069b4bb84a40226
3
+ size 31133
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51739794a631065dc342715b23b38cd583a2b306e00a2bb1ceab70162b38ba58
3
+ size 3055