Upload folder using huggingface_hub
Browse files
asr_tokenizer/special_tokens_map.json
CHANGED
|
@@ -1,89 +1,17 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
"single_word": false
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"content": "<zh>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"content": "<ja>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": false,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
},
|
| 31 |
-
{
|
| 32 |
-
"content": "<ko>",
|
| 33 |
-
"lstrip": false,
|
| 34 |
-
"normalized": false,
|
| 35 |
-
"rstrip": false,
|
| 36 |
-
"single_word": false
|
| 37 |
-
},
|
| 38 |
-
{
|
| 39 |
-
"content": "<en>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": false,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false
|
| 44 |
-
},
|
| 45 |
-
{
|
| 46 |
-
"content": "<fr>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"content": "<es>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"content": "<pt>",
|
| 61 |
-
"lstrip": false,
|
| 62 |
-
"normalized": false,
|
| 63 |
-
"rstrip": false,
|
| 64 |
-
"single_word": false
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"content": "<vi>",
|
| 68 |
-
"lstrip": false,
|
| 69 |
-
"normalized": false,
|
| 70 |
-
"rstrip": false,
|
| 71 |
-
"single_word": false
|
| 72 |
-
},
|
| 73 |
-
{
|
| 74 |
-
"content": "<id>",
|
| 75 |
-
"lstrip": false,
|
| 76 |
-
"normalized": false,
|
| 77 |
-
"rstrip": false,
|
| 78 |
-
"single_word": false
|
| 79 |
-
},
|
| 80 |
-
{
|
| 81 |
-
"content": "<ru>",
|
| 82 |
-
"lstrip": false,
|
| 83 |
-
"normalized": false,
|
| 84 |
-
"rstrip": false,
|
| 85 |
-
"single_word": false
|
| 86 |
-
}
|
| 87 |
],
|
| 88 |
"bos_token": {
|
| 89 |
"content": "<sos/eos>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"<transcribe>",
|
| 4 |
+
"<translate>",
|
| 5 |
+
"<zh>",
|
| 6 |
+
"<ja>",
|
| 7 |
+
"<ko>",
|
| 8 |
+
"<en>",
|
| 9 |
+
"<fr>",
|
| 10 |
+
"<es>",
|
| 11 |
+
"<pt>",
|
| 12 |
+
"<vi>",
|
| 13 |
+
"<id>",
|
| 14 |
+
"<ru>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
],
|
| 16 |
"bos_token": {
|
| 17 |
"content": "<sos/eos>",
|
asr_tokenizer/tokenizer.json
CHANGED
|
@@ -163,10 +163,26 @@
|
|
| 163 |
},
|
| 164 |
"post_processor": null,
|
| 165 |
"decoder": {
|
| 166 |
-
"type": "
|
| 167 |
-
"
|
| 168 |
-
|
| 169 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 170 |
},
|
| 171 |
"model": {
|
| 172 |
"type": "Unigram",
|
|
|
|
| 163 |
},
|
| 164 |
"post_processor": null,
|
| 165 |
"decoder": {
|
| 166 |
+
"type": "Sequence",
|
| 167 |
+
"decoders": [
|
| 168 |
+
{
|
| 169 |
+
"type": "Sequence",
|
| 170 |
+
"decoders": [
|
| 171 |
+
{
|
| 172 |
+
"type": "Metaspace",
|
| 173 |
+
"replacement": "▁",
|
| 174 |
+
"prepend_scheme": "always",
|
| 175 |
+
"split": true
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"type": "ByteFallback"
|
| 179 |
+
}
|
| 180 |
+
]
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"type": "ByteFallback"
|
| 184 |
+
}
|
| 185 |
+
]
|
| 186 |
},
|
| 187 |
"model": {
|
| 188 |
"type": "Unigram",
|