Commit
·
475b5cd
1
Parent(s):
a13606b
style
Browse files- generate_datasets.py +41 -13
generate_datasets.py
CHANGED
|
@@ -2,24 +2,53 @@ import json
|
|
| 2 |
import os
|
| 3 |
import shutil
|
| 4 |
|
| 5 |
-
import json
|
| 6 |
import requests
|
| 7 |
|
| 8 |
-
RELEASE_STATS_URL =
|
| 9 |
-
"https://commonvoice.mozilla.org/dist/releases/{}.json"
|
| 10 |
-
)
|
| 11 |
VERSIONS = [
|
| 12 |
{"semver": "1.0.0", "name": "common_voice_1_0", "release": "cv-corpus-1"},
|
| 13 |
{"semver": "2.0.0", "name": "common_voice_2_0", "release": "cv-corpus-2"},
|
| 14 |
{"semver": "3.0.0", "name": "common_voice_3_0", "release": "cv-corpus-3"},
|
| 15 |
-
{
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
{
|
| 21 |
-
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
]
|
| 24 |
|
| 25 |
|
|
@@ -93,4 +122,3 @@ def main():
|
|
| 93 |
|
| 94 |
if __name__ == "__main__":
|
| 95 |
main()
|
| 96 |
-
|
|
|
|
| 2 |
import os
|
| 3 |
import shutil
|
| 4 |
|
|
|
|
| 5 |
import requests
|
| 6 |
|
| 7 |
+
RELEASE_STATS_URL = "https://commonvoice.mozilla.org/dist/releases/{}.json"
|
|
|
|
|
|
|
| 8 |
VERSIONS = [
|
| 9 |
{"semver": "1.0.0", "name": "common_voice_1_0", "release": "cv-corpus-1"},
|
| 10 |
{"semver": "2.0.0", "name": "common_voice_2_0", "release": "cv-corpus-2"},
|
| 11 |
{"semver": "3.0.0", "name": "common_voice_3_0", "release": "cv-corpus-3"},
|
| 12 |
+
{
|
| 13 |
+
"semver": "4.0.0",
|
| 14 |
+
"name": "common_voice_4_0",
|
| 15 |
+
"release": "cv-corpus-4-2019-12-10",
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"semver": "5.0.0",
|
| 19 |
+
"name": "common_voice_5_0",
|
| 20 |
+
"release": "cv-corpus-5-2020-06-22",
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"semver": "5.1.0",
|
| 24 |
+
"name": "common_voice_5_1",
|
| 25 |
+
"release": "cv-corpus-5.1-2020-06-22",
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"semver": "6.0.0",
|
| 29 |
+
"name": "common_voice_6_0",
|
| 30 |
+
"release": "cv-corpus-6.0-2020-12-11",
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"semver": "6.1.0",
|
| 34 |
+
"name": "common_voice_6_1",
|
| 35 |
+
"release": "cv-corpus-6.1-2020-12-11",
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"semver": "7.0.0",
|
| 39 |
+
"name": "common_voice_7_0",
|
| 40 |
+
"release": "cv-corpus-7.0-2021-07-21",
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"semver": "8.0.0",
|
| 44 |
+
"name": "common_voice_8_0",
|
| 45 |
+
"release": "cv-corpus-8.0-2022-01-19",
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"semver": "9.0.0",
|
| 49 |
+
"name": "common_voice_9_0",
|
| 50 |
+
"release": "cv-corpus-9.0-2022-04-27",
|
| 51 |
+
},
|
| 52 |
]
|
| 53 |
|
| 54 |
|
|
|
|
| 122 |
|
| 123 |
if __name__ == "__main__":
|
| 124 |
main()
|
|
|