Revert "change g2p and other fix" (#40)

2023-09-30 09:13:39 +08:00
parent c3df0bab67
commit 2f687e4873
11 changed files with 253 additions and 75 deletions
--- a/bert/bert-large-japanese-v2/config.json
+++ b/bert/bert-large-japanese-v2/config.json
@@ -1,19 +0,0 @@
-{
-    "architectures": [
-        "BertForPreTraining"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 1024,
-    "initializer_range": 0.02,
-    "intermediate_size": 4096,
-    "layer_norm_eps": 1e-12,
-    "max_position_embeddings": 512,
-    "model_type": "bert",
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "pad_token_id": 0,
-    "type_vocab_size": 2,
-    "vocab_size": 32768
-}
--- a/bert/bert-large-japanese-v2/tokenizer_config.json
+++ b/bert/bert-large-japanese-v2/tokenizer_config.json
@@ -1,10 +0,0 @@
-{
-    "tokenizer_class": "BertJapaneseTokenizer",
-    "model_max_length": 512,
-    "do_lower_case": false,
-    "word_tokenizer_type": "mecab",
-    "subword_tokenizer_type": "wordpiece",
-    "mecab_kwargs": {
-        "mecab_dic": "unidic_lite"
-    }
-}
--- a/bert/bert-large-japanese-v2/vocab.txt
+++ b/bert/bert-large-japanese-v2/vocab.txt