move from cwkeam/mctc
Browse files- README.md +0 -0
- added_tokens.json +1 -0
- config.json +40 -0
- preprocessor_config.json +21 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
README.md
ADDED
File without changes
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 8065, "</s>": 8066}
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MCTCForCTC"
|
4 |
+
],
|
5 |
+
"attention_head_dim": 384,
|
6 |
+
"attention_probs_dropout_prob": 0.3,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"conv_channels": null,
|
9 |
+
"conv_dropout": 0.3,
|
10 |
+
"conv_glu_dim": 1,
|
11 |
+
"conv_kernel": [
|
12 |
+
7
|
13 |
+
],
|
14 |
+
"conv_stride": [
|
15 |
+
3
|
16 |
+
],
|
17 |
+
"ctc_loss_reduction": "sum",
|
18 |
+
"ctc_zero_infinity": false,
|
19 |
+
"eos_token_id": 2,
|
20 |
+
"hidden_act": "relu",
|
21 |
+
"hidden_dropout_prob": 0.3,
|
22 |
+
"hidden_size": 1536,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"input_channels": 1,
|
25 |
+
"input_feat_per_channel": 80,
|
26 |
+
"intermediate_size": 6144,
|
27 |
+
"layer_norm_eps": 1e-05,
|
28 |
+
"layerdrop": 0.3,
|
29 |
+
"max_position_embeddings": 920,
|
30 |
+
"model_type": "mctc",
|
31 |
+
"num_attention_heads": 4,
|
32 |
+
"num_conv_layers": 1,
|
33 |
+
"num_hidden_layers": 36,
|
34 |
+
"pad_token_id": 1,
|
35 |
+
"position_embedding_type": "relative_key",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.18.0.dev0",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 8065
|
40 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"K": 257,
|
3 |
+
"do_normalize": true,
|
4 |
+
"feature_extractor_type": "MCTCFeatureExtractor",
|
5 |
+
"feature_size": 80,
|
6 |
+
"frame_signal_scale": 32768.0,
|
7 |
+
"hop_length": 10,
|
8 |
+
"mel_floor": 1.0,
|
9 |
+
"n_fft": 512,
|
10 |
+
"normalize_means": true,
|
11 |
+
"normalize_vars": true,
|
12 |
+
"padding_side": "right",
|
13 |
+
"padding_value": 0.0,
|
14 |
+
"preemphasis_coeff": 0.97,
|
15 |
+
"return_attention_mask": false,
|
16 |
+
"sample_size": 400,
|
17 |
+
"sample_stride": 160,
|
18 |
+
"sampling_rate": 16000,
|
19 |
+
"win_function": "hamming_window",
|
20 |
+
"win_length": 25
|
21 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c72a45a7412319f841cc6c7fb2891657f7f37c4bab23cc5084a51d2796bf9a9d
|
3 |
+
size 4236090333
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "return_attention_mask": false, "do_normalize": true, "special_tokens_map_file": "./mctc-large/special_tokens_map.json", "name_or_path": "./mctc-large", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|