End of training
Browse files- README.md +86 -0
- added_tokens.json +92 -0
- config.json +48 -0
- generation_config.json +11 -0
- model.safetensors +3 -0
- preprocessor_config.json +16 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +57 -0
- tokenizer_config.json +860 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- ar
|
| 5 |
+
license: mit
|
| 6 |
+
base_model: facebook/s2t-medium-mustc-multilingual-st
|
| 7 |
+
tags:
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- darija-c
|
| 11 |
+
metrics:
|
| 12 |
+
- bleu
|
| 13 |
+
model-index:
|
| 14 |
+
- name: Finetuned-facebook-s2t-for-darija-speech-translation
|
| 15 |
+
results: []
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 19 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 20 |
+
|
| 21 |
+
# Finetuned-facebook-s2t-for-darija-speech-translation
|
| 22 |
+
|
| 23 |
+
This model is a fine-tuned version of [facebook/s2t-medium-mustc-multilingual-st](https://huggingface.co/facebook/s2t-medium-mustc-multilingual-st) on the Darija-C dataset.
|
| 24 |
+
It achieves the following results on the evaluation set:
|
| 25 |
+
- Loss: 5.7855
|
| 26 |
+
- Bleu: 0.0032
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 1e-05
|
| 46 |
+
- train_batch_size: 16
|
| 47 |
+
- eval_batch_size: 8
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_steps: 100
|
| 52 |
+
- training_steps: 1000
|
| 53 |
+
- mixed_precision_training: Native AMP
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 59 |
+
| 9.1689 | 12.5 | 50 | 8.4431 | 0.0 |
|
| 60 |
+
| 7.9984 | 25.0 | 100 | 7.6555 | 0.0 |
|
| 61 |
+
| 7.4717 | 37.5 | 150 | 7.2774 | 0.0 |
|
| 62 |
+
| 7.2484 | 50.0 | 200 | 7.1061 | 0.0 |
|
| 63 |
+
| 7.0982 | 62.5 | 250 | 6.9703 | 0.0 |
|
| 64 |
+
| 6.9724 | 75.0 | 300 | 6.8526 | 0.0011 |
|
| 65 |
+
| 6.8564 | 87.5 | 350 | 6.7225 | 0.0034 |
|
| 66 |
+
| 6.7332 | 100.0 | 400 | 6.6144 | 0.0034 |
|
| 67 |
+
| 6.6511 | 112.5 | 450 | 6.5264 | 0.0034 |
|
| 68 |
+
| 6.5283 | 125.0 | 500 | 6.4174 | 0.0034 |
|
| 69 |
+
| 6.4477 | 137.5 | 550 | 6.3187 | 0.0034 |
|
| 70 |
+
| 6.3455 | 150.0 | 600 | 6.2208 | 0.0031 |
|
| 71 |
+
| 6.2683 | 162.5 | 650 | 6.0831 | 0.0034 |
|
| 72 |
+
| 6.1757 | 175.0 | 700 | 6.0449 | 0.0032 |
|
| 73 |
+
| 6.1017 | 187.5 | 750 | 5.9507 | 0.0034 |
|
| 74 |
+
| 6.0438 | 200.0 | 800 | 5.8899 | 0.0032 |
|
| 75 |
+
| 5.9752 | 212.5 | 850 | 5.8447 | 0.0034 |
|
| 76 |
+
| 5.9657 | 225.0 | 900 | 5.8105 | 0.0032 |
|
| 77 |
+
| 5.925 | 237.5 | 950 | 5.7858 | 0.0032 |
|
| 78 |
+
| 5.9142 | 250.0 | 1000 | 5.7855 | 0.0032 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.47.1
|
| 84 |
+
- Pytorch 2.5.1+cu121
|
| 85 |
+
- Datasets 2.19.2
|
| 86 |
+
- Tokenizers 0.21.0
|
added_tokens.json
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[UNK]": 10089,
|
| 3 |
+
"آريد": 10025,
|
| 4 |
+
"أحد": 10056,
|
| 5 |
+
"أراك": 10047,
|
| 6 |
+
"أغضبتني": 10042,
|
| 7 |
+
"أكرهك": 10006,
|
| 8 |
+
"أنا": 10009,
|
| 9 |
+
"أنت": 10059,
|
| 10 |
+
"أو": 10033,
|
| 11 |
+
"إذا": 10014,
|
| 12 |
+
"إنهض": 10011,
|
| 13 |
+
"ابتهج": 10046,
|
| 14 |
+
"اتصل": 10082,
|
| 15 |
+
"اجلس": 10052,
|
| 16 |
+
"احبك": 10037,
|
| 17 |
+
"احذر": 10005,
|
| 18 |
+
"اختفيتي": 10040,
|
| 19 |
+
"اكرهك": 10045,
|
| 20 |
+
"الأزقة": 10032,
|
| 21 |
+
"الأمر": 10066,
|
| 22 |
+
"الحارس": 10051,
|
| 23 |
+
"الخير": 10024,
|
| 24 |
+
"الرجاء": 10077,
|
| 25 |
+
"الشئ": 10030,
|
| 26 |
+
"الشوارع": 10034,
|
| 27 |
+
"الضيقة": 10035,
|
| 28 |
+
"القادمة": 10049,
|
| 29 |
+
"الكبريت": 10000,
|
| 30 |
+
"الكرة": 10039,
|
| 31 |
+
"المرة": 10048,
|
| 32 |
+
"الناس": 10019,
|
| 33 |
+
"امس": 10003,
|
| 34 |
+
"امشِ": 10007,
|
| 35 |
+
"انا": 10036,
|
| 36 |
+
"بالخرف": 10087,
|
| 37 |
+
"بخير": 10010,
|
| 38 |
+
"بسرعة": 10061,
|
| 39 |
+
"بلقائك": 10065,
|
| 40 |
+
"بي": 10083,
|
| 41 |
+
"تتحرك": 10074,
|
| 42 |
+
"ترقص": 10004,
|
| 43 |
+
"تسير": 10060,
|
| 44 |
+
"تعال": 10084,
|
| 45 |
+
"تقلق": 10073,
|
| 46 |
+
"تكرار": 10078,
|
| 47 |
+
"جميل": 10075,
|
| 48 |
+
"حالك": 10044,
|
| 49 |
+
"حبوب": 10063,
|
| 50 |
+
"خلاص": 10001,
|
| 51 |
+
"دائم": 10053,
|
| 52 |
+
"ذلك؟": 10079,
|
| 53 |
+
"رايح": 10041,
|
| 54 |
+
"رجع": 10015,
|
| 55 |
+
"سعيد": 10064,
|
| 56 |
+
"شيء": 10058,
|
| 57 |
+
"صيني": 10002,
|
| 58 |
+
"عليك": 10071,
|
| 59 |
+
"فهمت": 10022,
|
| 60 |
+
"قبيح": 10080,
|
| 61 |
+
"كاعية": 10031,
|
| 62 |
+
"كبيرة": 10062,
|
| 63 |
+
"كذا": 10020,
|
| 64 |
+
"كلام": 10050,
|
| 65 |
+
"كن": 10026,
|
| 66 |
+
"كيف": 10043,
|
| 67 |
+
"لا": 10072,
|
| 68 |
+
"لايوجد": 10055,
|
| 69 |
+
"لقد": 10021,
|
| 70 |
+
"لك": 10068,
|
| 71 |
+
"ليس": 10057,
|
| 72 |
+
"ماذا": 10012,
|
| 73 |
+
"ماهذا": 10085,
|
| 74 |
+
"متروك": 10067,
|
| 75 |
+
"متى": 10054,
|
| 76 |
+
"مساء": 10023,
|
| 77 |
+
"مستحيل": 10028,
|
| 78 |
+
"مصاب": 10086,
|
| 79 |
+
"ملعب": 10038,
|
| 80 |
+
"نام": 10081,
|
| 81 |
+
"نمسكه": 10018,
|
| 82 |
+
"ننتظر": 10008,
|
| 83 |
+
"هادئ": 10027,
|
| 84 |
+
"هذا": 10029,
|
| 85 |
+
"هـل": 10016,
|
| 86 |
+
"هناك": 10013,
|
| 87 |
+
"هيا": 10017,
|
| 88 |
+
"يشتغل": 10088,
|
| 89 |
+
"يقبضون": 10070,
|
| 90 |
+
"يمسكوك": 10069,
|
| 91 |
+
"يمكنك": 10076
|
| 92 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/s2t-medium-mustc-multilingual-st",
|
| 3 |
+
"activation_dropout": 0.15,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Speech2TextForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.15,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"conv_channels": 1024,
|
| 12 |
+
"conv_kernel_sizes": [
|
| 13 |
+
5,
|
| 14 |
+
5
|
| 15 |
+
],
|
| 16 |
+
"d_model": 512,
|
| 17 |
+
"decoder_attention_heads": 8,
|
| 18 |
+
"decoder_ffn_dim": 2048,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 6,
|
| 21 |
+
"decoder_start_token_id": 2,
|
| 22 |
+
"dropout": 0.15,
|
| 23 |
+
"early_stopping": null,
|
| 24 |
+
"encoder_attention_heads": 8,
|
| 25 |
+
"encoder_ffn_dim": 2048,
|
| 26 |
+
"encoder_layerdrop": 0.0,
|
| 27 |
+
"encoder_layers": 12,
|
| 28 |
+
"eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"init_std": 0.02,
|
| 31 |
+
"input_channels": 1,
|
| 32 |
+
"input_feat_per_channel": 80,
|
| 33 |
+
"is_encoder_decoder": true,
|
| 34 |
+
"max_length": null,
|
| 35 |
+
"max_source_positions": 6000,
|
| 36 |
+
"max_target_positions": 1024,
|
| 37 |
+
"model_type": "speech_to_text",
|
| 38 |
+
"num_beams": null,
|
| 39 |
+
"num_conv_layers": 2,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"pad_token_id": 1,
|
| 42 |
+
"scale_embedding": true,
|
| 43 |
+
"tie_word_embeddings": false,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.47.1",
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 10090
|
| 48 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"max_length": 200,
|
| 8 |
+
"num_beams": 5,
|
| 9 |
+
"pad_token_id": 1,
|
| 10 |
+
"transformers_version": "4.47.1"
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6ac490335817da17357511b73d803ecb5487f6c1267187d98f702ae8df29b57
|
| 3 |
+
size 320115008
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_ceptral_normalize": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"feature_extractor_type": "Speech2TextFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"norm_means": true,
|
| 7 |
+
"norm_vars": true,
|
| 8 |
+
"normalize_means": true,
|
| 9 |
+
"normalize_vars": true,
|
| 10 |
+
"num_mel_bins": 80,
|
| 11 |
+
"padding_side": "right",
|
| 12 |
+
"padding_value": 0.0,
|
| 13 |
+
"processor_class": "Speech2TextProcessor",
|
| 14 |
+
"return_attention_mask": true,
|
| 15 |
+
"sampling_rate": 16000
|
| 16 |
+
}
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccd9bc57fef83ec633abb6496fa47c9660891b9acca2b487671395dba2173772
|
| 3 |
+
size 410393
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<lang:pt>",
|
| 4 |
+
"<lang:fr>",
|
| 5 |
+
"<lang:ru>",
|
| 6 |
+
"<lang:nl>",
|
| 7 |
+
"<lang:ro>",
|
| 8 |
+
"<lang:it>",
|
| 9 |
+
"<lang:es>",
|
| 10 |
+
"<lang:de>",
|
| 11 |
+
"<lang:pt>",
|
| 12 |
+
"<lang:fr>",
|
| 13 |
+
"<lang:ru>",
|
| 14 |
+
"<lang:nl>",
|
| 15 |
+
"<lang:ro>",
|
| 16 |
+
"<lang:it>",
|
| 17 |
+
"<lang:es>",
|
| 18 |
+
"<lang:de>",
|
| 19 |
+
"<lang:pt>",
|
| 20 |
+
"<lang:fr>",
|
| 21 |
+
"<lang:ru>",
|
| 22 |
+
"<lang:nl>",
|
| 23 |
+
"<lang:ro>",
|
| 24 |
+
"<lang:it>",
|
| 25 |
+
"<lang:es>",
|
| 26 |
+
"<lang:de>",
|
| 27 |
+
"[UNK]"
|
| 28 |
+
],
|
| 29 |
+
"bos_token": {
|
| 30 |
+
"content": "<s>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"eos_token": {
|
| 37 |
+
"content": "</s>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false
|
| 42 |
+
},
|
| 43 |
+
"pad_token": {
|
| 44 |
+
"content": "<pad>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false
|
| 49 |
+
},
|
| 50 |
+
"unk_token": {
|
| 51 |
+
"content": "<unk>",
|
| 52 |
+
"lstrip": false,
|
| 53 |
+
"normalized": false,
|
| 54 |
+
"rstrip": false,
|
| 55 |
+
"single_word": false
|
| 56 |
+
}
|
| 57 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,860 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<lang:pt>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "<lang:fr>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "<lang:ru>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "<lang:nl>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "<lang:ro>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "<lang:it>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "<lang:es>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "<lang:de>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"10000": {
|
| 100 |
+
"content": "الكبريت",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"10001": {
|
| 108 |
+
"content": "خلاص",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"10002": {
|
| 116 |
+
"content": "صيني",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"10003": {
|
| 124 |
+
"content": "امس",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"10004": {
|
| 132 |
+
"content": "ترقص",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"10005": {
|
| 140 |
+
"content": "احذر",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"10006": {
|
| 148 |
+
"content": "أكرهك",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"10007": {
|
| 156 |
+
"content": "امشِ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"10008": {
|
| 164 |
+
"content": "ننتظر",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"10009": {
|
| 172 |
+
"content": "أنا",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"10010": {
|
| 180 |
+
"content": "بخير",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"10011": {
|
| 188 |
+
"content": "إنهض",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"10012": {
|
| 196 |
+
"content": "ماذا",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"10013": {
|
| 204 |
+
"content": "هناك",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"10014": {
|
| 212 |
+
"content": "إذا",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"10015": {
|
| 220 |
+
"content": "رجع",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": false
|
| 226 |
+
},
|
| 227 |
+
"10016": {
|
| 228 |
+
"content": "هـل",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": false
|
| 234 |
+
},
|
| 235 |
+
"10017": {
|
| 236 |
+
"content": "هيا",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": false
|
| 242 |
+
},
|
| 243 |
+
"10018": {
|
| 244 |
+
"content": "نمسكه",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": true,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": false
|
| 250 |
+
},
|
| 251 |
+
"10019": {
|
| 252 |
+
"content": "الناس",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": true,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": false
|
| 258 |
+
},
|
| 259 |
+
"10020": {
|
| 260 |
+
"content": "كذا",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": true,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": false
|
| 266 |
+
},
|
| 267 |
+
"10021": {
|
| 268 |
+
"content": "لقد",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"10022": {
|
| 276 |
+
"content": "فهمت",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"10023": {
|
| 284 |
+
"content": "مساء",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"10024": {
|
| 292 |
+
"content": "الخير",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"10025": {
|
| 300 |
+
"content": "آريد",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"10026": {
|
| 308 |
+
"content": "كن",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"10027": {
|
| 316 |
+
"content": "هادئ",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"10028": {
|
| 324 |
+
"content": "مستحيل",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"10029": {
|
| 332 |
+
"content": "هذا",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"10030": {
|
| 340 |
+
"content": "الشئ",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"10031": {
|
| 348 |
+
"content": "كاعية",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"10032": {
|
| 356 |
+
"content": "الأزقة",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"10033": {
|
| 364 |
+
"content": "أو",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"10034": {
|
| 372 |
+
"content": "الشوارع",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"10035": {
|
| 380 |
+
"content": "الضيقة",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"10036": {
|
| 388 |
+
"content": "انا",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"10037": {
|
| 396 |
+
"content": "احبك",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"10038": {
|
| 404 |
+
"content": "ملعب",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"10039": {
|
| 412 |
+
"content": "الكرة",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"10040": {
|
| 420 |
+
"content": "اختفيتي",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"10041": {
|
| 428 |
+
"content": "رايح",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"10042": {
|
| 436 |
+
"content": "أغضبتني",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"10043": {
|
| 444 |
+
"content": "كيف",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"10044": {
|
| 452 |
+
"content": "حالك",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"10045": {
|
| 460 |
+
"content": "اكرهك",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"10046": {
|
| 468 |
+
"content": "ابتهج",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"10047": {
|
| 476 |
+
"content": "أراك",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"10048": {
|
| 484 |
+
"content": "المرة",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"10049": {
|
| 492 |
+
"content": "القادمة",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"10050": {
|
| 500 |
+
"content": "كلام",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"10051": {
|
| 508 |
+
"content": "الحارس",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"10052": {
|
| 516 |
+
"content": "اجلس",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"10053": {
|
| 524 |
+
"content": "دائم",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"10054": {
|
| 532 |
+
"content": "متى",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"10055": {
|
| 540 |
+
"content": "لايوجد",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"10056": {
|
| 548 |
+
"content": "أحد",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"10057": {
|
| 556 |
+
"content": "ليس",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"10058": {
|
| 564 |
+
"content": "شيء",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"10059": {
|
| 572 |
+
"content": "أنت",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"10060": {
|
| 580 |
+
"content": "تسير",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"10061": {
|
| 588 |
+
"content": "بسرعة",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"10062": {
|
| 596 |
+
"content": "كبيرة",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"10063": {
|
| 604 |
+
"content": "حبوب",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"10064": {
|
| 612 |
+
"content": "سعيد",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"10065": {
|
| 620 |
+
"content": "بلقائك",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"10066": {
|
| 628 |
+
"content": "الأمر",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"10067": {
|
| 636 |
+
"content": "متروك",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"10068": {
|
| 644 |
+
"content": "لك",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"10069": {
|
| 652 |
+
"content": "يمسكوك",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"10070": {
|
| 660 |
+
"content": "يقبضون",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"10071": {
|
| 668 |
+
"content": "عليك",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"10072": {
|
| 676 |
+
"content": "لا",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"10073": {
|
| 684 |
+
"content": "تقلق",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"10074": {
|
| 692 |
+
"content": "تتحرك",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"10075": {
|
| 700 |
+
"content": "جميل",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"10076": {
|
| 708 |
+
"content": "يمكنك",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"10077": {
|
| 716 |
+
"content": "الرجاء",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"10078": {
|
| 724 |
+
"content": "تكرار",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"10079": {
|
| 732 |
+
"content": "ذلك؟",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"10080": {
|
| 740 |
+
"content": "قبيح",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"10081": {
|
| 748 |
+
"content": "نام",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"10082": {
|
| 756 |
+
"content": "اتصل",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"10083": {
|
| 764 |
+
"content": "بي",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"10084": {
|
| 772 |
+
"content": "تعال",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"10085": {
|
| 780 |
+
"content": "ماهذا",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"10086": {
|
| 788 |
+
"content": "مصاب",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"10087": {
|
| 796 |
+
"content": "بالخرف",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"10088": {
|
| 804 |
+
"content": "يشتغل",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"10089": {
|
| 812 |
+
"content": "[UNK]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
}
|
| 819 |
+
},
|
| 820 |
+
"additional_special_tokens": [
|
| 821 |
+
"<lang:pt>",
|
| 822 |
+
"<lang:fr>",
|
| 823 |
+
"<lang:ru>",
|
| 824 |
+
"<lang:nl>",
|
| 825 |
+
"<lang:ro>",
|
| 826 |
+
"<lang:it>",
|
| 827 |
+
"<lang:es>",
|
| 828 |
+
"<lang:de>",
|
| 829 |
+
"<lang:pt>",
|
| 830 |
+
"<lang:fr>",
|
| 831 |
+
"<lang:ru>",
|
| 832 |
+
"<lang:nl>",
|
| 833 |
+
"<lang:ro>",
|
| 834 |
+
"<lang:it>",
|
| 835 |
+
"<lang:es>",
|
| 836 |
+
"<lang:de>",
|
| 837 |
+
"<lang:pt>",
|
| 838 |
+
"<lang:fr>",
|
| 839 |
+
"<lang:ru>",
|
| 840 |
+
"<lang:nl>",
|
| 841 |
+
"<lang:ro>",
|
| 842 |
+
"<lang:it>",
|
| 843 |
+
"<lang:es>",
|
| 844 |
+
"<lang:de>",
|
| 845 |
+
"[UNK]"
|
| 846 |
+
],
|
| 847 |
+
"bos_token": "<s>",
|
| 848 |
+
"clean_up_tokenization_spaces": false,
|
| 849 |
+
"do_lower_case": false,
|
| 850 |
+
"do_upper_case": false,
|
| 851 |
+
"eos_token": "</s>",
|
| 852 |
+
"extra_special_tokens": {},
|
| 853 |
+
"lang_codes": "mustc",
|
| 854 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 855 |
+
"pad_token": "<pad>",
|
| 856 |
+
"sp_model_kwargs": {},
|
| 857 |
+
"tgt_lang": "pt",
|
| 858 |
+
"tokenizer_class": "Speech2TextTokenizer",
|
| 859 |
+
"unk_token": "<unk>"
|
| 860 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16e44452bbb9409a31659a9dabae34a04b6c5b3ba8d2f33a9371024df6450d78
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|