chore: clone vinai/PhoWhisper-base
Browse files- .gitattributes +1 -0
- README.md +0 -22
- config.json +3 -2
- generation_config.json +1 -2
- onnx/decoder_model_bnb4.onnx +0 -3
- onnx/decoder_model_fp16.onnx +0 -3
- onnx/decoder_model_int8.onnx +0 -3
- onnx/decoder_model_merged.onnx +0 -3
- onnx/decoder_model_merged_bnb4.onnx +0 -3
- onnx/decoder_model_merged_fp16.onnx +0 -3
- onnx/decoder_model_merged_int8.onnx +0 -3
- onnx/decoder_model_merged_q4.onnx +0 -3
- onnx/decoder_model_merged_quantized.onnx +0 -3
- onnx/decoder_model_merged_uint8.onnx +0 -3
- onnx/decoder_model_q4.onnx +0 -3
- onnx/decoder_model_quantized.onnx +0 -3
- onnx/decoder_model_uint8.onnx +0 -3
- onnx/decoder_with_past_model.onnx +0 -3
- onnx/decoder_with_past_model_bnb4.onnx +0 -3
- onnx/decoder_with_past_model_fp16.onnx +0 -3
- onnx/decoder_with_past_model_int8.onnx +0 -3
- onnx/decoder_with_past_model_q4.onnx +0 -3
- onnx/decoder_with_past_model_quantized.onnx +0 -3
- onnx/decoder_with_past_model_uint8.onnx +0 -3
- onnx/encoder_model.onnx +0 -3
- onnx/encoder_model_bnb4.onnx +0 -3
- onnx/encoder_model_fp16.onnx +0 -3
- onnx/encoder_model_int8.onnx +0 -3
- onnx/encoder_model_q4.onnx +0 -3
- onnx/encoder_model_quantized.onnx +0 -3
- onnx/encoder_model_uint8.onnx +0 -3
- onnx/decoder_model.onnx → pytorch_model.bin +2 -2
- special_tokens_map.json +4 -10
- tokenizer_config.json +24 -970
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -1 +1,2 @@
|
|
|
|
|
| 1 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 1 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 2 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,25 +1,3 @@
|
|
| 1 |
-
---
|
| 2 |
-
language:
|
| 3 |
-
- vi
|
| 4 |
-
tags:
|
| 5 |
-
- audio
|
| 6 |
-
- automatic-speech-recognition
|
| 7 |
-
- hf-asr-leaderboard
|
| 8 |
-
library_name: transformers.js
|
| 9 |
-
pipeline_tag: automatic-speech-recognition
|
| 10 |
-
widget:
|
| 11 |
-
- example_title: Librispeech sample 1
|
| 12 |
-
src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
|
| 13 |
-
- example_title: Librispeech sample 2
|
| 14 |
-
src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
|
| 15 |
-
license: wtfpl
|
| 16 |
-
---
|
| 17 |
-
|
| 18 |
-
https://hf.co/vinai/PhoWhisper-base with ONNX weights to be compatible with Transformers.js.
|
| 19 |
-
|
| 20 |
-
Please check out this demo using the model:
|
| 21 |
-
[](https://huggingface.co/spaces/huuquyet/PhoWhisper-next)
|
| 22 |
-
|
| 23 |
# PhoWhisper: Automatic Speech Recognition for Vietnamese
|
| 24 |
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# PhoWhisper: Automatic Speech Recognition for Vietnamese
|
| 2 |
|
| 3 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
|
@@ -43,7 +43,8 @@
|
|
| 43 |
"num_mel_bins": 80,
|
| 44 |
"pad_token_id": 50257,
|
| 45 |
"scale_embedding": false,
|
| 46 |
-
"
|
|
|
|
| 47 |
"use_cache": true,
|
| 48 |
"use_weighted_layer_sum": false,
|
| 49 |
"vocab_size": 51865
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "./finetuned_models_FINAL/whisper-base-vi/checkpoint-6000",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
|
|
|
| 43 |
"num_mel_bins": 80,
|
| 44 |
"pad_token_id": 50257,
|
| 45 |
"scale_embedding": false,
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.31.0",
|
| 48 |
"use_cache": true,
|
| 49 |
"use_weighted_layer_sum": false,
|
| 50 |
"vocab_size": 51865
|
generation_config.json
CHANGED
|
@@ -251,6 +251,5 @@
|
|
| 251 |
"transcribe": 50359,
|
| 252 |
"translate": 50358
|
| 253 |
},
|
| 254 |
-
"transformers_version": "4.
|
| 255 |
-
"trust_remote_code": false
|
| 256 |
}
|
|
|
|
| 251 |
"transcribe": 50359,
|
| 252 |
"translate": 50358
|
| 253 |
},
|
| 254 |
+
"transformers_version": "4.31.0"
|
|
|
|
| 255 |
}
|
onnx/decoder_model_bnb4.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:68c2e286d0c3e95e5620ab9dd487dce34b091c94348504b624bf8723e7ed79fd
|
| 3 |
-
size 121791631
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_fp16.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:046420e8db940c1efb4c7d2be78eae59c26a89fbe48e502ba8346cbaee038457
|
| 3 |
-
size 104396174
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_int8.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a0e142815b58c4515d6aa7d67c9dd2c668da2afaeab152d655652b650507d450
|
| 3 |
-
size 53310178
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_merged.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f5ab9b5333682f91ca4ca13012149e89d906c94036b37ad5d8d9c1a7f9ce894a
|
| 3 |
-
size 208521528
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_merged_bnb4.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:77bfcbaaf6465eaa18a5127d8c18b5a9f48544283e0f8833d24b18583496edb6
|
| 3 |
-
size 122030467
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_merged_fp16.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4399583669d3d6802708a014a14022e4737a999039f70377862ff484af5d82f0
|
| 3 |
-
size 104722354
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_merged_int8.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:09824fa165c230d6af1df9d1e30148a08dcef080447bb4bd5108853a5950a41a
|
| 3 |
-
size 53693315
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_merged_q4.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4da59eed743c0df7302e7e3ed16288a81fea3583b6c47e6dd9914fda16934b9e
|
| 3 |
-
size 123602419
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_merged_quantized.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:09824fa165c230d6af1df9d1e30148a08dcef080447bb4bd5108853a5950a41a
|
| 3 |
-
size 53693315
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_merged_uint8.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5adcec696b04effbe4d0355b6f6217121356715f26216d8bb8be3803e7cde4ea
|
| 3 |
-
size 53693344
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_q4.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0d6685fdbbb667bfbfbe3a7935d7824e59aaee03d82ee3d434983ddec7516143
|
| 3 |
-
size 123364015
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_quantized.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a0e142815b58c4515d6aa7d67c9dd2c668da2afaeab152d655652b650507d450
|
| 3 |
-
size 53310178
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model_uint8.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9c079dc6b427ea83cdcd4013d5b16c3be62e66deed5495a6b54cd7077cbd847d
|
| 3 |
-
size 53310207
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_with_past_model.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:dd365ad7252f648e1d0c1f2ef82e16e82e2843c89a4e544c3c30bba9571c9642
|
| 3 |
-
size 195647494
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_with_past_model_bnb4.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:636c8a6bdc8f973d8c76bc9de7d57ae3b86fab1e83ef4e3baf5ecba07823fd34
|
| 3 |
-
size 119960957
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_with_past_model_fp16.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bb24e77b63a49cd3716537985d9dfc595ce0d452caaf7921e535224bbbabe688
|
| 3 |
-
size 98035209
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_with_past_model_int8.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a44b2ea755073236dfe9cb6d8f6ba44b46fd71b3e18dbacaa1dd869d8666d0b9
|
| 3 |
-
size 50075136
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_with_past_model_q4.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:43568aa3a7a094615e80d1692a57c80a49b6352937ce662126314c8fe7905053
|
| 3 |
-
size 121336829
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_with_past_model_quantized.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a44b2ea755073236dfe9cb6d8f6ba44b46fd71b3e18dbacaa1dd869d8666d0b9
|
| 3 |
-
size 50075136
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_with_past_model_uint8.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8a52ef68fbdbe098b458bff482070348e7620d3926ddce79b72ad4cc45f3f131
|
| 3 |
-
size 50075160
|
|
|
|
|
|
|
|
|
|
|
|
onnx/encoder_model.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:052ef143ad5ef3278479b47e9e960c2510c19163cd9774e2ce275c5e1ee38859
|
| 3 |
-
size 82468078
|
|
|
|
|
|
|
|
|
|
|
|
onnx/encoder_model_bnb4.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:897d4397f5546baba8ea94caa2d7ffef3d966b9815c0d6eae173ef33c230dbf4
|
| 3 |
-
size 17593091
|
|
|
|
|
|
|
|
|
|
|
|
onnx/encoder_model_fp16.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bfd0409adedf3dd1a2acc0f9c471ef605dfadd0f99151faba9a0672b3b05abe6
|
| 3 |
-
size 41332612
|
|
|
|
|
|
|
|
|
|
|
|
onnx/encoder_model_int8.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f9eb3dfd8fcbba04ef5497aa5cd62d1cb1973e5481b0e88a3424679d41416f20
|
| 3 |
-
size 23201297
|
|
|
|
|
|
|
|
|
|
|
|
onnx/encoder_model_q4.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fba51e812ef4ec3fea85cf5babcecaca79ad9c3776ff3db99ec3d0287175f183
|
| 3 |
-
size 18772451
|
|
|
|
|
|
|
|
|
|
|
|
onnx/encoder_model_quantized.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f8ec714b54851c844b30539204c883f8a3ef072a2df9b010aea8845964009e9d
|
| 3 |
-
size 23201315
|
|
|
|
|
|
|
|
|
|
|
|
onnx/encoder_model_uint8.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f8ec714b54851c844b30539204c883f8a3ef072a2df9b010aea8845964009e9d
|
| 3 |
-
size 23201315
|
|
|
|
|
|
|
|
|
|
|
|
onnx/decoder_model.onnx → pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:910b9e8875497078efa83dc506ea7ee378e4e759a206ceecbf23e088aec9b9f8
|
| 3 |
+
size 290458785
|
special_tokens_map.json
CHANGED
|
@@ -111,28 +111,22 @@
|
|
| 111 |
"bos_token": {
|
| 112 |
"content": "<|endoftext|>",
|
| 113 |
"lstrip": false,
|
| 114 |
-
"normalized":
|
| 115 |
"rstrip": false,
|
| 116 |
"single_word": false
|
| 117 |
},
|
| 118 |
"eos_token": {
|
| 119 |
"content": "<|endoftext|>",
|
| 120 |
"lstrip": false,
|
| 121 |
-
"normalized":
|
| 122 |
-
"rstrip": false,
|
| 123 |
-
"single_word": false
|
| 124 |
-
},
|
| 125 |
-
"pad_token": {
|
| 126 |
-
"content": "<|endoftext|>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
"rstrip": false,
|
| 130 |
"single_word": false
|
| 131 |
},
|
|
|
|
| 132 |
"unk_token": {
|
| 133 |
"content": "<|endoftext|>",
|
| 134 |
"lstrip": false,
|
| 135 |
-
"normalized":
|
| 136 |
"rstrip": false,
|
| 137 |
"single_word": false
|
| 138 |
}
|
|
|
|
| 111 |
"bos_token": {
|
| 112 |
"content": "<|endoftext|>",
|
| 113 |
"lstrip": false,
|
| 114 |
+
"normalized": true,
|
| 115 |
"rstrip": false,
|
| 116 |
"single_word": false
|
| 117 |
},
|
| 118 |
"eos_token": {
|
| 119 |
"content": "<|endoftext|>",
|
| 120 |
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
"rstrip": false,
|
| 123 |
"single_word": false
|
| 124 |
},
|
| 125 |
+
"pad_token": "<|endoftext|>",
|
| 126 |
"unk_token": {
|
| 127 |
"content": "<|endoftext|>",
|
| 128 |
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
"rstrip": false,
|
| 131 |
"single_word": false
|
| 132 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,981 +1,35 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"50258": {
|
| 14 |
-
"content": "<|startoftranscript|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"50259": {
|
| 22 |
-
"content": "<|en|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"50260": {
|
| 30 |
-
"content": "<|zh|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"50261": {
|
| 38 |
-
"content": "<|de|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"50262": {
|
| 46 |
-
"content": "<|es|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"50263": {
|
| 54 |
-
"content": "<|ru|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"50264": {
|
| 62 |
-
"content": "<|ko|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"50265": {
|
| 70 |
-
"content": "<|fr|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"50266": {
|
| 78 |
-
"content": "<|ja|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"50267": {
|
| 86 |
-
"content": "<|pt|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"50268": {
|
| 94 |
-
"content": "<|tr|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"50269": {
|
| 102 |
-
"content": "<|pl|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"50270": {
|
| 110 |
-
"content": "<|ca|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"50271": {
|
| 118 |
-
"content": "<|nl|>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": true
|
| 124 |
-
},
|
| 125 |
-
"50272": {
|
| 126 |
-
"content": "<|ar|>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": true
|
| 132 |
-
},
|
| 133 |
-
"50273": {
|
| 134 |
-
"content": "<|sv|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": true
|
| 140 |
-
},
|
| 141 |
-
"50274": {
|
| 142 |
-
"content": "<|it|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": true
|
| 148 |
-
},
|
| 149 |
-
"50275": {
|
| 150 |
-
"content": "<|id|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": true
|
| 156 |
-
},
|
| 157 |
-
"50276": {
|
| 158 |
-
"content": "<|hi|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": true
|
| 164 |
-
},
|
| 165 |
-
"50277": {
|
| 166 |
-
"content": "<|fi|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": true
|
| 172 |
-
},
|
| 173 |
-
"50278": {
|
| 174 |
-
"content": "<|vi|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": true
|
| 180 |
-
},
|
| 181 |
-
"50279": {
|
| 182 |
-
"content": "<|he|>",
|
| 183 |
-
"lstrip": false,
|
| 184 |
-
"normalized": false,
|
| 185 |
-
"rstrip": false,
|
| 186 |
-
"single_word": false,
|
| 187 |
-
"special": true
|
| 188 |
-
},
|
| 189 |
-
"50280": {
|
| 190 |
-
"content": "<|uk|>",
|
| 191 |
-
"lstrip": false,
|
| 192 |
-
"normalized": false,
|
| 193 |
-
"rstrip": false,
|
| 194 |
-
"single_word": false,
|
| 195 |
-
"special": true
|
| 196 |
-
},
|
| 197 |
-
"50281": {
|
| 198 |
-
"content": "<|el|>",
|
| 199 |
-
"lstrip": false,
|
| 200 |
-
"normalized": false,
|
| 201 |
-
"rstrip": false,
|
| 202 |
-
"single_word": false,
|
| 203 |
-
"special": true
|
| 204 |
-
},
|
| 205 |
-
"50282": {
|
| 206 |
-
"content": "<|ms|>",
|
| 207 |
-
"lstrip": false,
|
| 208 |
-
"normalized": false,
|
| 209 |
-
"rstrip": false,
|
| 210 |
-
"single_word": false,
|
| 211 |
-
"special": true
|
| 212 |
-
},
|
| 213 |
-
"50283": {
|
| 214 |
-
"content": "<|cs|>",
|
| 215 |
-
"lstrip": false,
|
| 216 |
-
"normalized": false,
|
| 217 |
-
"rstrip": false,
|
| 218 |
-
"single_word": false,
|
| 219 |
-
"special": true
|
| 220 |
-
},
|
| 221 |
-
"50284": {
|
| 222 |
-
"content": "<|ro|>",
|
| 223 |
-
"lstrip": false,
|
| 224 |
-
"normalized": false,
|
| 225 |
-
"rstrip": false,
|
| 226 |
-
"single_word": false,
|
| 227 |
-
"special": true
|
| 228 |
-
},
|
| 229 |
-
"50285": {
|
| 230 |
-
"content": "<|da|>",
|
| 231 |
-
"lstrip": false,
|
| 232 |
-
"normalized": false,
|
| 233 |
-
"rstrip": false,
|
| 234 |
-
"single_word": false,
|
| 235 |
-
"special": true
|
| 236 |
-
},
|
| 237 |
-
"50286": {
|
| 238 |
-
"content": "<|hu|>",
|
| 239 |
-
"lstrip": false,
|
| 240 |
-
"normalized": false,
|
| 241 |
-
"rstrip": false,
|
| 242 |
-
"single_word": false,
|
| 243 |
-
"special": true
|
| 244 |
-
},
|
| 245 |
-
"50287": {
|
| 246 |
-
"content": "<|ta|>",
|
| 247 |
-
"lstrip": false,
|
| 248 |
-
"normalized": false,
|
| 249 |
-
"rstrip": false,
|
| 250 |
-
"single_word": false,
|
| 251 |
-
"special": true
|
| 252 |
-
},
|
| 253 |
-
"50288": {
|
| 254 |
-
"content": "<|no|>",
|
| 255 |
-
"lstrip": false,
|
| 256 |
-
"normalized": false,
|
| 257 |
-
"rstrip": false,
|
| 258 |
-
"single_word": false,
|
| 259 |
-
"special": true
|
| 260 |
-
},
|
| 261 |
-
"50289": {
|
| 262 |
-
"content": "<|th|>",
|
| 263 |
-
"lstrip": false,
|
| 264 |
-
"normalized": false,
|
| 265 |
-
"rstrip": false,
|
| 266 |
-
"single_word": false,
|
| 267 |
-
"special": true
|
| 268 |
-
},
|
| 269 |
-
"50290": {
|
| 270 |
-
"content": "<|ur|>",
|
| 271 |
-
"lstrip": false,
|
| 272 |
-
"normalized": false,
|
| 273 |
-
"rstrip": false,
|
| 274 |
-
"single_word": false,
|
| 275 |
-
"special": true
|
| 276 |
-
},
|
| 277 |
-
"50291": {
|
| 278 |
-
"content": "<|hr|>",
|
| 279 |
-
"lstrip": false,
|
| 280 |
-
"normalized": false,
|
| 281 |
-
"rstrip": false,
|
| 282 |
-
"single_word": false,
|
| 283 |
-
"special": true
|
| 284 |
-
},
|
| 285 |
-
"50292": {
|
| 286 |
-
"content": "<|bg|>",
|
| 287 |
-
"lstrip": false,
|
| 288 |
-
"normalized": false,
|
| 289 |
-
"rstrip": false,
|
| 290 |
-
"single_word": false,
|
| 291 |
-
"special": true
|
| 292 |
-
},
|
| 293 |
-
"50293": {
|
| 294 |
-
"content": "<|lt|>",
|
| 295 |
-
"lstrip": false,
|
| 296 |
-
"normalized": false,
|
| 297 |
-
"rstrip": false,
|
| 298 |
-
"single_word": false,
|
| 299 |
-
"special": true
|
| 300 |
-
},
|
| 301 |
-
"50294": {
|
| 302 |
-
"content": "<|la|>",
|
| 303 |
-
"lstrip": false,
|
| 304 |
-
"normalized": false,
|
| 305 |
-
"rstrip": false,
|
| 306 |
-
"single_word": false,
|
| 307 |
-
"special": true
|
| 308 |
-
},
|
| 309 |
-
"50295": {
|
| 310 |
-
"content": "<|mi|>",
|
| 311 |
-
"lstrip": false,
|
| 312 |
-
"normalized": false,
|
| 313 |
-
"rstrip": false,
|
| 314 |
-
"single_word": false,
|
| 315 |
-
"special": true
|
| 316 |
-
},
|
| 317 |
-
"50296": {
|
| 318 |
-
"content": "<|ml|>",
|
| 319 |
-
"lstrip": false,
|
| 320 |
-
"normalized": false,
|
| 321 |
-
"rstrip": false,
|
| 322 |
-
"single_word": false,
|
| 323 |
-
"special": true
|
| 324 |
-
},
|
| 325 |
-
"50297": {
|
| 326 |
-
"content": "<|cy|>",
|
| 327 |
-
"lstrip": false,
|
| 328 |
-
"normalized": false,
|
| 329 |
-
"rstrip": false,
|
| 330 |
-
"single_word": false,
|
| 331 |
-
"special": true
|
| 332 |
-
},
|
| 333 |
-
"50298": {
|
| 334 |
-
"content": "<|sk|>",
|
| 335 |
-
"lstrip": false,
|
| 336 |
-
"normalized": false,
|
| 337 |
-
"rstrip": false,
|
| 338 |
-
"single_word": false,
|
| 339 |
-
"special": true
|
| 340 |
-
},
|
| 341 |
-
"50299": {
|
| 342 |
-
"content": "<|te|>",
|
| 343 |
-
"lstrip": false,
|
| 344 |
-
"normalized": false,
|
| 345 |
-
"rstrip": false,
|
| 346 |
-
"single_word": false,
|
| 347 |
-
"special": true
|
| 348 |
-
},
|
| 349 |
-
"50300": {
|
| 350 |
-
"content": "<|fa|>",
|
| 351 |
-
"lstrip": false,
|
| 352 |
-
"normalized": false,
|
| 353 |
-
"rstrip": false,
|
| 354 |
-
"single_word": false,
|
| 355 |
-
"special": true
|
| 356 |
-
},
|
| 357 |
-
"50301": {
|
| 358 |
-
"content": "<|lv|>",
|
| 359 |
-
"lstrip": false,
|
| 360 |
-
"normalized": false,
|
| 361 |
-
"rstrip": false,
|
| 362 |
-
"single_word": false,
|
| 363 |
-
"special": true
|
| 364 |
-
},
|
| 365 |
-
"50302": {
|
| 366 |
-
"content": "<|bn|>",
|
| 367 |
-
"lstrip": false,
|
| 368 |
-
"normalized": false,
|
| 369 |
-
"rstrip": false,
|
| 370 |
-
"single_word": false,
|
| 371 |
-
"special": true
|
| 372 |
-
},
|
| 373 |
-
"50303": {
|
| 374 |
-
"content": "<|sr|>",
|
| 375 |
-
"lstrip": false,
|
| 376 |
-
"normalized": false,
|
| 377 |
-
"rstrip": false,
|
| 378 |
-
"single_word": false,
|
| 379 |
-
"special": true
|
| 380 |
-
},
|
| 381 |
-
"50304": {
|
| 382 |
-
"content": "<|az|>",
|
| 383 |
-
"lstrip": false,
|
| 384 |
-
"normalized": false,
|
| 385 |
-
"rstrip": false,
|
| 386 |
-
"single_word": false,
|
| 387 |
-
"special": true
|
| 388 |
-
},
|
| 389 |
-
"50305": {
|
| 390 |
-
"content": "<|sl|>",
|
| 391 |
-
"lstrip": false,
|
| 392 |
-
"normalized": false,
|
| 393 |
-
"rstrip": false,
|
| 394 |
-
"single_word": false,
|
| 395 |
-
"special": true
|
| 396 |
-
},
|
| 397 |
-
"50306": {
|
| 398 |
-
"content": "<|kn|>",
|
| 399 |
-
"lstrip": false,
|
| 400 |
-
"normalized": false,
|
| 401 |
-
"rstrip": false,
|
| 402 |
-
"single_word": false,
|
| 403 |
-
"special": true
|
| 404 |
-
},
|
| 405 |
-
"50307": {
|
| 406 |
-
"content": "<|et|>",
|
| 407 |
-
"lstrip": false,
|
| 408 |
-
"normalized": false,
|
| 409 |
-
"rstrip": false,
|
| 410 |
-
"single_word": false,
|
| 411 |
-
"special": true
|
| 412 |
-
},
|
| 413 |
-
"50308": {
|
| 414 |
-
"content": "<|mk|>",
|
| 415 |
-
"lstrip": false,
|
| 416 |
-
"normalized": false,
|
| 417 |
-
"rstrip": false,
|
| 418 |
-
"single_word": false,
|
| 419 |
-
"special": true
|
| 420 |
-
},
|
| 421 |
-
"50309": {
|
| 422 |
-
"content": "<|br|>",
|
| 423 |
-
"lstrip": false,
|
| 424 |
-
"normalized": false,
|
| 425 |
-
"rstrip": false,
|
| 426 |
-
"single_word": false,
|
| 427 |
-
"special": true
|
| 428 |
-
},
|
| 429 |
-
"50310": {
|
| 430 |
-
"content": "<|eu|>",
|
| 431 |
-
"lstrip": false,
|
| 432 |
-
"normalized": false,
|
| 433 |
-
"rstrip": false,
|
| 434 |
-
"single_word": false,
|
| 435 |
-
"special": true
|
| 436 |
-
},
|
| 437 |
-
"50311": {
|
| 438 |
-
"content": "<|is|>",
|
| 439 |
-
"lstrip": false,
|
| 440 |
-
"normalized": false,
|
| 441 |
-
"rstrip": false,
|
| 442 |
-
"single_word": false,
|
| 443 |
-
"special": true
|
| 444 |
-
},
|
| 445 |
-
"50312": {
|
| 446 |
-
"content": "<|hy|>",
|
| 447 |
-
"lstrip": false,
|
| 448 |
-
"normalized": false,
|
| 449 |
-
"rstrip": false,
|
| 450 |
-
"single_word": false,
|
| 451 |
-
"special": true
|
| 452 |
-
},
|
| 453 |
-
"50313": {
|
| 454 |
-
"content": "<|ne|>",
|
| 455 |
-
"lstrip": false,
|
| 456 |
-
"normalized": false,
|
| 457 |
-
"rstrip": false,
|
| 458 |
-
"single_word": false,
|
| 459 |
-
"special": true
|
| 460 |
-
},
|
| 461 |
-
"50314": {
|
| 462 |
-
"content": "<|mn|>",
|
| 463 |
-
"lstrip": false,
|
| 464 |
-
"normalized": false,
|
| 465 |
-
"rstrip": false,
|
| 466 |
-
"single_word": false,
|
| 467 |
-
"special": true
|
| 468 |
-
},
|
| 469 |
-
"50315": {
|
| 470 |
-
"content": "<|bs|>",
|
| 471 |
-
"lstrip": false,
|
| 472 |
-
"normalized": false,
|
| 473 |
-
"rstrip": false,
|
| 474 |
-
"single_word": false,
|
| 475 |
-
"special": true
|
| 476 |
-
},
|
| 477 |
-
"50316": {
|
| 478 |
-
"content": "<|kk|>",
|
| 479 |
-
"lstrip": false,
|
| 480 |
-
"normalized": false,
|
| 481 |
-
"rstrip": false,
|
| 482 |
-
"single_word": false,
|
| 483 |
-
"special": true
|
| 484 |
-
},
|
| 485 |
-
"50317": {
|
| 486 |
-
"content": "<|sq|>",
|
| 487 |
-
"lstrip": false,
|
| 488 |
-
"normalized": false,
|
| 489 |
-
"rstrip": false,
|
| 490 |
-
"single_word": false,
|
| 491 |
-
"special": true
|
| 492 |
-
},
|
| 493 |
-
"50318": {
|
| 494 |
-
"content": "<|sw|>",
|
| 495 |
-
"lstrip": false,
|
| 496 |
-
"normalized": false,
|
| 497 |
-
"rstrip": false,
|
| 498 |
-
"single_word": false,
|
| 499 |
-
"special": true
|
| 500 |
-
},
|
| 501 |
-
"50319": {
|
| 502 |
-
"content": "<|gl|>",
|
| 503 |
-
"lstrip": false,
|
| 504 |
-
"normalized": false,
|
| 505 |
-
"rstrip": false,
|
| 506 |
-
"single_word": false,
|
| 507 |
-
"special": true
|
| 508 |
-
},
|
| 509 |
-
"50320": {
|
| 510 |
-
"content": "<|mr|>",
|
| 511 |
-
"lstrip": false,
|
| 512 |
-
"normalized": false,
|
| 513 |
-
"rstrip": false,
|
| 514 |
-
"single_word": false,
|
| 515 |
-
"special": true
|
| 516 |
-
},
|
| 517 |
-
"50321": {
|
| 518 |
-
"content": "<|pa|>",
|
| 519 |
-
"lstrip": false,
|
| 520 |
-
"normalized": false,
|
| 521 |
-
"rstrip": false,
|
| 522 |
-
"single_word": false,
|
| 523 |
-
"special": true
|
| 524 |
-
},
|
| 525 |
-
"50322": {
|
| 526 |
-
"content": "<|si|>",
|
| 527 |
-
"lstrip": false,
|
| 528 |
-
"normalized": false,
|
| 529 |
-
"rstrip": false,
|
| 530 |
-
"single_word": false,
|
| 531 |
-
"special": true
|
| 532 |
-
},
|
| 533 |
-
"50323": {
|
| 534 |
-
"content": "<|km|>",
|
| 535 |
-
"lstrip": false,
|
| 536 |
-
"normalized": false,
|
| 537 |
-
"rstrip": false,
|
| 538 |
-
"single_word": false,
|
| 539 |
-
"special": true
|
| 540 |
-
},
|
| 541 |
-
"50324": {
|
| 542 |
-
"content": "<|sn|>",
|
| 543 |
-
"lstrip": false,
|
| 544 |
-
"normalized": false,
|
| 545 |
-
"rstrip": false,
|
| 546 |
-
"single_word": false,
|
| 547 |
-
"special": true
|
| 548 |
-
},
|
| 549 |
-
"50325": {
|
| 550 |
-
"content": "<|yo|>",
|
| 551 |
-
"lstrip": false,
|
| 552 |
-
"normalized": false,
|
| 553 |
-
"rstrip": false,
|
| 554 |
-
"single_word": false,
|
| 555 |
-
"special": true
|
| 556 |
-
},
|
| 557 |
-
"50326": {
|
| 558 |
-
"content": "<|so|>",
|
| 559 |
-
"lstrip": false,
|
| 560 |
-
"normalized": false,
|
| 561 |
-
"rstrip": false,
|
| 562 |
-
"single_word": false,
|
| 563 |
-
"special": true
|
| 564 |
-
},
|
| 565 |
-
"50327": {
|
| 566 |
-
"content": "<|af|>",
|
| 567 |
-
"lstrip": false,
|
| 568 |
-
"normalized": false,
|
| 569 |
-
"rstrip": false,
|
| 570 |
-
"single_word": false,
|
| 571 |
-
"special": true
|
| 572 |
-
},
|
| 573 |
-
"50328": {
|
| 574 |
-
"content": "<|oc|>",
|
| 575 |
-
"lstrip": false,
|
| 576 |
-
"normalized": false,
|
| 577 |
-
"rstrip": false,
|
| 578 |
-
"single_word": false,
|
| 579 |
-
"special": true
|
| 580 |
-
},
|
| 581 |
-
"50329": {
|
| 582 |
-
"content": "<|ka|>",
|
| 583 |
-
"lstrip": false,
|
| 584 |
-
"normalized": false,
|
| 585 |
-
"rstrip": false,
|
| 586 |
-
"single_word": false,
|
| 587 |
-
"special": true
|
| 588 |
-
},
|
| 589 |
-
"50330": {
|
| 590 |
-
"content": "<|be|>",
|
| 591 |
-
"lstrip": false,
|
| 592 |
-
"normalized": false,
|
| 593 |
-
"rstrip": false,
|
| 594 |
-
"single_word": false,
|
| 595 |
-
"special": true
|
| 596 |
-
},
|
| 597 |
-
"50331": {
|
| 598 |
-
"content": "<|tg|>",
|
| 599 |
-
"lstrip": false,
|
| 600 |
-
"normalized": false,
|
| 601 |
-
"rstrip": false,
|
| 602 |
-
"single_word": false,
|
| 603 |
-
"special": true
|
| 604 |
-
},
|
| 605 |
-
"50332": {
|
| 606 |
-
"content": "<|sd|>",
|
| 607 |
-
"lstrip": false,
|
| 608 |
-
"normalized": false,
|
| 609 |
-
"rstrip": false,
|
| 610 |
-
"single_word": false,
|
| 611 |
-
"special": true
|
| 612 |
-
},
|
| 613 |
-
"50333": {
|
| 614 |
-
"content": "<|gu|>",
|
| 615 |
-
"lstrip": false,
|
| 616 |
-
"normalized": false,
|
| 617 |
-
"rstrip": false,
|
| 618 |
-
"single_word": false,
|
| 619 |
-
"special": true
|
| 620 |
-
},
|
| 621 |
-
"50334": {
|
| 622 |
-
"content": "<|am|>",
|
| 623 |
-
"lstrip": false,
|
| 624 |
-
"normalized": false,
|
| 625 |
-
"rstrip": false,
|
| 626 |
-
"single_word": false,
|
| 627 |
-
"special": true
|
| 628 |
-
},
|
| 629 |
-
"50335": {
|
| 630 |
-
"content": "<|yi|>",
|
| 631 |
-
"lstrip": false,
|
| 632 |
-
"normalized": false,
|
| 633 |
-
"rstrip": false,
|
| 634 |
-
"single_word": false,
|
| 635 |
-
"special": true
|
| 636 |
-
},
|
| 637 |
-
"50336": {
|
| 638 |
-
"content": "<|lo|>",
|
| 639 |
-
"lstrip": false,
|
| 640 |
-
"normalized": false,
|
| 641 |
-
"rstrip": false,
|
| 642 |
-
"single_word": false,
|
| 643 |
-
"special": true
|
| 644 |
-
},
|
| 645 |
-
"50337": {
|
| 646 |
-
"content": "<|uz|>",
|
| 647 |
-
"lstrip": false,
|
| 648 |
-
"normalized": false,
|
| 649 |
-
"rstrip": false,
|
| 650 |
-
"single_word": false,
|
| 651 |
-
"special": true
|
| 652 |
-
},
|
| 653 |
-
"50338": {
|
| 654 |
-
"content": "<|fo|>",
|
| 655 |
-
"lstrip": false,
|
| 656 |
-
"normalized": false,
|
| 657 |
-
"rstrip": false,
|
| 658 |
-
"single_word": false,
|
| 659 |
-
"special": true
|
| 660 |
-
},
|
| 661 |
-
"50339": {
|
| 662 |
-
"content": "<|ht|>",
|
| 663 |
-
"lstrip": false,
|
| 664 |
-
"normalized": false,
|
| 665 |
-
"rstrip": false,
|
| 666 |
-
"single_word": false,
|
| 667 |
-
"special": true
|
| 668 |
-
},
|
| 669 |
-
"50340": {
|
| 670 |
-
"content": "<|ps|>",
|
| 671 |
-
"lstrip": false,
|
| 672 |
-
"normalized": false,
|
| 673 |
-
"rstrip": false,
|
| 674 |
-
"single_word": false,
|
| 675 |
-
"special": true
|
| 676 |
-
},
|
| 677 |
-
"50341": {
|
| 678 |
-
"content": "<|tk|>",
|
| 679 |
-
"lstrip": false,
|
| 680 |
-
"normalized": false,
|
| 681 |
-
"rstrip": false,
|
| 682 |
-
"single_word": false,
|
| 683 |
-
"special": true
|
| 684 |
-
},
|
| 685 |
-
"50342": {
|
| 686 |
-
"content": "<|nn|>",
|
| 687 |
-
"lstrip": false,
|
| 688 |
-
"normalized": false,
|
| 689 |
-
"rstrip": false,
|
| 690 |
-
"single_word": false,
|
| 691 |
-
"special": true
|
| 692 |
-
},
|
| 693 |
-
"50343": {
|
| 694 |
-
"content": "<|mt|>",
|
| 695 |
-
"lstrip": false,
|
| 696 |
-
"normalized": false,
|
| 697 |
-
"rstrip": false,
|
| 698 |
-
"single_word": false,
|
| 699 |
-
"special": true
|
| 700 |
-
},
|
| 701 |
-
"50344": {
|
| 702 |
-
"content": "<|sa|>",
|
| 703 |
-
"lstrip": false,
|
| 704 |
-
"normalized": false,
|
| 705 |
-
"rstrip": false,
|
| 706 |
-
"single_word": false,
|
| 707 |
-
"special": true
|
| 708 |
-
},
|
| 709 |
-
"50345": {
|
| 710 |
-
"content": "<|lb|>",
|
| 711 |
-
"lstrip": false,
|
| 712 |
-
"normalized": false,
|
| 713 |
-
"rstrip": false,
|
| 714 |
-
"single_word": false,
|
| 715 |
-
"special": true
|
| 716 |
-
},
|
| 717 |
-
"50346": {
|
| 718 |
-
"content": "<|my|>",
|
| 719 |
-
"lstrip": false,
|
| 720 |
-
"normalized": false,
|
| 721 |
-
"rstrip": false,
|
| 722 |
-
"single_word": false,
|
| 723 |
-
"special": true
|
| 724 |
-
},
|
| 725 |
-
"50347": {
|
| 726 |
-
"content": "<|bo|>",
|
| 727 |
-
"lstrip": false,
|
| 728 |
-
"normalized": false,
|
| 729 |
-
"rstrip": false,
|
| 730 |
-
"single_word": false,
|
| 731 |
-
"special": true
|
| 732 |
-
},
|
| 733 |
-
"50348": {
|
| 734 |
-
"content": "<|tl|>",
|
| 735 |
-
"lstrip": false,
|
| 736 |
-
"normalized": false,
|
| 737 |
-
"rstrip": false,
|
| 738 |
-
"single_word": false,
|
| 739 |
-
"special": true
|
| 740 |
-
},
|
| 741 |
-
"50349": {
|
| 742 |
-
"content": "<|mg|>",
|
| 743 |
-
"lstrip": false,
|
| 744 |
-
"normalized": false,
|
| 745 |
-
"rstrip": false,
|
| 746 |
-
"single_word": false,
|
| 747 |
-
"special": true
|
| 748 |
-
},
|
| 749 |
-
"50350": {
|
| 750 |
-
"content": "<|as|>",
|
| 751 |
-
"lstrip": false,
|
| 752 |
-
"normalized": false,
|
| 753 |
-
"rstrip": false,
|
| 754 |
-
"single_word": false,
|
| 755 |
-
"special": true
|
| 756 |
-
},
|
| 757 |
-
"50351": {
|
| 758 |
-
"content": "<|tt|>",
|
| 759 |
-
"lstrip": false,
|
| 760 |
-
"normalized": false,
|
| 761 |
-
"rstrip": false,
|
| 762 |
-
"single_word": false,
|
| 763 |
-
"special": true
|
| 764 |
-
},
|
| 765 |
-
"50352": {
|
| 766 |
-
"content": "<|haw|>",
|
| 767 |
-
"lstrip": false,
|
| 768 |
-
"normalized": false,
|
| 769 |
-
"rstrip": false,
|
| 770 |
-
"single_word": false,
|
| 771 |
-
"special": true
|
| 772 |
-
},
|
| 773 |
-
"50353": {
|
| 774 |
-
"content": "<|ln|>",
|
| 775 |
-
"lstrip": false,
|
| 776 |
-
"normalized": false,
|
| 777 |
-
"rstrip": false,
|
| 778 |
-
"single_word": false,
|
| 779 |
-
"special": true
|
| 780 |
-
},
|
| 781 |
-
"50354": {
|
| 782 |
-
"content": "<|ha|>",
|
| 783 |
-
"lstrip": false,
|
| 784 |
-
"normalized": false,
|
| 785 |
-
"rstrip": false,
|
| 786 |
-
"single_word": false,
|
| 787 |
-
"special": true
|
| 788 |
-
},
|
| 789 |
-
"50355": {
|
| 790 |
-
"content": "<|ba|>",
|
| 791 |
-
"lstrip": false,
|
| 792 |
-
"normalized": false,
|
| 793 |
-
"rstrip": false,
|
| 794 |
-
"single_word": false,
|
| 795 |
-
"special": true
|
| 796 |
-
},
|
| 797 |
-
"50356": {
|
| 798 |
-
"content": "<|jw|>",
|
| 799 |
-
"lstrip": false,
|
| 800 |
-
"normalized": false,
|
| 801 |
-
"rstrip": false,
|
| 802 |
-
"single_word": false,
|
| 803 |
-
"special": true
|
| 804 |
-
},
|
| 805 |
-
"50357": {
|
| 806 |
-
"content": "<|su|>",
|
| 807 |
-
"lstrip": false,
|
| 808 |
-
"normalized": false,
|
| 809 |
-
"rstrip": false,
|
| 810 |
-
"single_word": false,
|
| 811 |
-
"special": true
|
| 812 |
-
},
|
| 813 |
-
"50358": {
|
| 814 |
-
"content": "<|translate|>",
|
| 815 |
-
"lstrip": false,
|
| 816 |
-
"normalized": false,
|
| 817 |
-
"rstrip": false,
|
| 818 |
-
"single_word": false,
|
| 819 |
-
"special": true
|
| 820 |
-
},
|
| 821 |
-
"50359": {
|
| 822 |
-
"content": "<|transcribe|>",
|
| 823 |
-
"lstrip": false,
|
| 824 |
-
"normalized": false,
|
| 825 |
-
"rstrip": false,
|
| 826 |
-
"single_word": false,
|
| 827 |
-
"special": true
|
| 828 |
-
},
|
| 829 |
-
"50360": {
|
| 830 |
-
"content": "<|startoflm|>",
|
| 831 |
-
"lstrip": false,
|
| 832 |
-
"normalized": false,
|
| 833 |
-
"rstrip": false,
|
| 834 |
-
"single_word": false,
|
| 835 |
-
"special": true
|
| 836 |
-
},
|
| 837 |
-
"50361": {
|
| 838 |
-
"content": "<|startofprev|>",
|
| 839 |
-
"lstrip": false,
|
| 840 |
-
"normalized": false,
|
| 841 |
-
"rstrip": false,
|
| 842 |
-
"single_word": false,
|
| 843 |
-
"special": true
|
| 844 |
-
},
|
| 845 |
-
"50362": {
|
| 846 |
-
"content": "<|nocaptions|>",
|
| 847 |
-
"lstrip": false,
|
| 848 |
-
"normalized": false,
|
| 849 |
-
"rstrip": false,
|
| 850 |
-
"single_word": false,
|
| 851 |
-
"special": true
|
| 852 |
-
},
|
| 853 |
-
"50363": {
|
| 854 |
-
"content": "<|notimestamps|>",
|
| 855 |
-
"lstrip": false,
|
| 856 |
-
"normalized": false,
|
| 857 |
-
"rstrip": false,
|
| 858 |
-
"single_word": false,
|
| 859 |
-
"special": true
|
| 860 |
-
}
|
| 861 |
},
|
| 862 |
-
"additional_special_tokens": [
|
| 863 |
-
"<|endoftext|>",
|
| 864 |
-
"<|startoftranscript|>",
|
| 865 |
-
"<|en|>",
|
| 866 |
-
"<|zh|>",
|
| 867 |
-
"<|de|>",
|
| 868 |
-
"<|es|>",
|
| 869 |
-
"<|ru|>",
|
| 870 |
-
"<|ko|>",
|
| 871 |
-
"<|fr|>",
|
| 872 |
-
"<|ja|>",
|
| 873 |
-
"<|pt|>",
|
| 874 |
-
"<|tr|>",
|
| 875 |
-
"<|pl|>",
|
| 876 |
-
"<|ca|>",
|
| 877 |
-
"<|nl|>",
|
| 878 |
-
"<|ar|>",
|
| 879 |
-
"<|sv|>",
|
| 880 |
-
"<|it|>",
|
| 881 |
-
"<|id|>",
|
| 882 |
-
"<|hi|>",
|
| 883 |
-
"<|fi|>",
|
| 884 |
-
"<|vi|>",
|
| 885 |
-
"<|he|>",
|
| 886 |
-
"<|uk|>",
|
| 887 |
-
"<|el|>",
|
| 888 |
-
"<|ms|>",
|
| 889 |
-
"<|cs|>",
|
| 890 |
-
"<|ro|>",
|
| 891 |
-
"<|da|>",
|
| 892 |
-
"<|hu|>",
|
| 893 |
-
"<|ta|>",
|
| 894 |
-
"<|no|>",
|
| 895 |
-
"<|th|>",
|
| 896 |
-
"<|ur|>",
|
| 897 |
-
"<|hr|>",
|
| 898 |
-
"<|bg|>",
|
| 899 |
-
"<|lt|>",
|
| 900 |
-
"<|la|>",
|
| 901 |
-
"<|mi|>",
|
| 902 |
-
"<|ml|>",
|
| 903 |
-
"<|cy|>",
|
| 904 |
-
"<|sk|>",
|
| 905 |
-
"<|te|>",
|
| 906 |
-
"<|fa|>",
|
| 907 |
-
"<|lv|>",
|
| 908 |
-
"<|bn|>",
|
| 909 |
-
"<|sr|>",
|
| 910 |
-
"<|az|>",
|
| 911 |
-
"<|sl|>",
|
| 912 |
-
"<|kn|>",
|
| 913 |
-
"<|et|>",
|
| 914 |
-
"<|mk|>",
|
| 915 |
-
"<|br|>",
|
| 916 |
-
"<|eu|>",
|
| 917 |
-
"<|is|>",
|
| 918 |
-
"<|hy|>",
|
| 919 |
-
"<|ne|>",
|
| 920 |
-
"<|mn|>",
|
| 921 |
-
"<|bs|>",
|
| 922 |
-
"<|kk|>",
|
| 923 |
-
"<|sq|>",
|
| 924 |
-
"<|sw|>",
|
| 925 |
-
"<|gl|>",
|
| 926 |
-
"<|mr|>",
|
| 927 |
-
"<|pa|>",
|
| 928 |
-
"<|si|>",
|
| 929 |
-
"<|km|>",
|
| 930 |
-
"<|sn|>",
|
| 931 |
-
"<|yo|>",
|
| 932 |
-
"<|so|>",
|
| 933 |
-
"<|af|>",
|
| 934 |
-
"<|oc|>",
|
| 935 |
-
"<|ka|>",
|
| 936 |
-
"<|be|>",
|
| 937 |
-
"<|tg|>",
|
| 938 |
-
"<|sd|>",
|
| 939 |
-
"<|gu|>",
|
| 940 |
-
"<|am|>",
|
| 941 |
-
"<|yi|>",
|
| 942 |
-
"<|lo|>",
|
| 943 |
-
"<|uz|>",
|
| 944 |
-
"<|fo|>",
|
| 945 |
-
"<|ht|>",
|
| 946 |
-
"<|ps|>",
|
| 947 |
-
"<|tk|>",
|
| 948 |
-
"<|nn|>",
|
| 949 |
-
"<|mt|>",
|
| 950 |
-
"<|sa|>",
|
| 951 |
-
"<|lb|>",
|
| 952 |
-
"<|my|>",
|
| 953 |
-
"<|bo|>",
|
| 954 |
-
"<|tl|>",
|
| 955 |
-
"<|mg|>",
|
| 956 |
-
"<|as|>",
|
| 957 |
-
"<|tt|>",
|
| 958 |
-
"<|haw|>",
|
| 959 |
-
"<|ln|>",
|
| 960 |
-
"<|ha|>",
|
| 961 |
-
"<|ba|>",
|
| 962 |
-
"<|jw|>",
|
| 963 |
-
"<|su|>",
|
| 964 |
-
"<|translate|>",
|
| 965 |
-
"<|transcribe|>",
|
| 966 |
-
"<|startoflm|>",
|
| 967 |
-
"<|startofprev|>",
|
| 968 |
-
"<|nocaptions|>",
|
| 969 |
-
"<|notimestamps|>"
|
| 970 |
-
],
|
| 971 |
-
"bos_token": "<|endoftext|>",
|
| 972 |
"clean_up_tokenization_spaces": true,
|
| 973 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 974 |
"errors": "replace",
|
| 975 |
"model_max_length": 448,
|
| 976 |
-
"pad_token":
|
| 977 |
"processor_class": "WhisperProcessor",
|
| 978 |
"return_attention_mask": false,
|
| 979 |
"tokenizer_class": "WhisperTokenizer",
|
| 980 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 981 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"clean_up_tokenization_spaces": true,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
"errors": "replace",
|
| 22 |
"model_max_length": 448,
|
| 23 |
+
"pad_token": null,
|
| 24 |
"processor_class": "WhisperProcessor",
|
| 25 |
"return_attention_mask": false,
|
| 26 |
"tokenizer_class": "WhisperTokenizer",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"__type": "AddedToken",
|
| 29 |
+
"content": "<|endoftext|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|