add files
Browse files- README.md +0 -0
- config.json +47 -0
- preprocessor_config.json +14 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
README.md
ADDED
File without changes
|
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hf_models/s2t_mustc_multilinguial_medium",
|
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": true,
|
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": 200,
|
35 |
+
"max_source_positions": 6000,
|
36 |
+
"max_target_positions": 1024,
|
37 |
+
"model_type": "speech_to_text",
|
38 |
+
"num_beams": 5,
|
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 |
+
"transformers_version": "4.4.0.dev0",
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 10000
|
47 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_ceptral_normalize": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"feature_size": 80,
|
5 |
+
"norm_means": true,
|
6 |
+
"norm_vars": true,
|
7 |
+
"normalize_means": true,
|
8 |
+
"normalize_vars": true,
|
9 |
+
"num_mel_bins": 80,
|
10 |
+
"padding_side": "right",
|
11 |
+
"padding_value": 0.0,
|
12 |
+
"return_attention_mask": true,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8e8e048f2b01c9a988e8d1b4e8a9538505f75b3dc0a4d6a1b7b956b75da0001
|
3 |
+
size 305434117
|
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 @@
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<lang:pt>", "<lang:fr>", "<lang:ru>", "<lang:nl>", "<lang:ro>", "<lang:it>", "<lang:es>", "<lang:de>"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "do_upper_case": false, "do_lower_case": false, "tgt_lang": null, "lang_codes": "mustc", "special_tokens_map_file": "hf_models/s2t_mustc_multilinguial_medium/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "hf_models/s2t_mustc_multilinguial_medium"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|