Commit
•
f393a08
1
Parent(s):
ee55d1e
Upload tiny models for SpeechT5ForSpeechToText
Browse files- added_tokens.json +4 -0
- preprocessor_config.json +23 -0
- special_tokens_map.json +13 -0
- spm_char.model +3 -0
- tokenizer_config.json +12 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<ctc_blank>": 80,
|
3 |
+
"<mask>": 79
|
4 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": false,
|
3 |
+
"feature_extractor_type": "SpeechT5FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"fmax": 7600,
|
6 |
+
"fmin": 80,
|
7 |
+
"frame_signal_scale": 1.0,
|
8 |
+
"hop_length": 16,
|
9 |
+
"mel_floor": 1e-10,
|
10 |
+
"n_fft": 1024,
|
11 |
+
"n_freqs": 513,
|
12 |
+
"num_mel_bins": 80,
|
13 |
+
"padding_side": "right",
|
14 |
+
"padding_value": 0.0,
|
15 |
+
"processor_class": "SpeechT5Processor",
|
16 |
+
"reduction_factor": 2,
|
17 |
+
"return_attention_mask": true,
|
18 |
+
"sample_size": 1024,
|
19 |
+
"sample_stride": 256,
|
20 |
+
"sampling_rate": 16000,
|
21 |
+
"win_function": "hann_window",
|
22 |
+
"win_length": 64
|
23 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": {
|
5 |
+
"content": "<mask>",
|
6 |
+
"lstrip": true,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"pad_token": "<pad>",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
spm_char.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
|
3 |
+
size 238473
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 450,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"processor_class": "SpeechT5Processor",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"special_tokens_map_file": "/home/runner/.cache/huggingface/hub/models--microsoft--speecht5_asr/snapshots/53615c10408485422e09a12cda191a747f4bbe34/special_tokens_map.json",
|
10 |
+
"tokenizer_class": "SpeechT5Tokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|