Commit
•
014705d
1
Parent(s):
bf16ee0
Upload processor
Browse files- merges.txt +0 -0
- preprocessor_config.json +22 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
- vocab.json +0 -0
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length_s": 10,
|
3 |
+
"feature_extractor_type": "ClapFeatureExtractor",
|
4 |
+
"feature_size": 64,
|
5 |
+
"fft_window_size": 1024,
|
6 |
+
"frequency_max": 14000,
|
7 |
+
"frequency_min": 50,
|
8 |
+
"hop_length": 480,
|
9 |
+
"max_length_s": 10,
|
10 |
+
"n_fft": 1024,
|
11 |
+
"nb_frequency_bins": 513,
|
12 |
+
"nb_max_frames": 1000,
|
13 |
+
"nb_max_samples": 480000,
|
14 |
+
"padding": "repeatpad",
|
15 |
+
"padding_side": "right",
|
16 |
+
"padding_value": 0.0,
|
17 |
+
"processor_class": "ClapProcessor",
|
18 |
+
"return_attention_mask": false,
|
19 |
+
"sampling_rate": 48000,
|
20 |
+
"top_db": null,
|
21 |
+
"truncation": "rand_trunc"
|
22 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"model_max_length": 512,
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"processor_class": "ClapProcessor",
|
12 |
+
"sep_token": "</s>",
|
13 |
+
"special_tokens_map_file": null,
|
14 |
+
"tokenizer_class": "RobertaTokenizer",
|
15 |
+
"trim_offsets": true,
|
16 |
+
"trust_remote_code": false,
|
17 |
+
"unk_token": "<unk>"
|
18 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|