From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/build_utils/build_lm_model.py | 17 +++++++++++------
1 files changed, 11 insertions(+), 6 deletions(-)
diff --git a/funasr/build_utils/build_lm_model.py b/funasr/build_utils/build_lm_model.py
index aaa4fb7..f78a20e 100644
--- a/funasr/build_utils/build_lm_model.py
+++ b/funasr/build_utils/build_lm_model.py
@@ -1,9 +1,9 @@
import logging
-from funasr.lm.abs_model import AbsLM
-from funasr.lm.abs_model import LanguageModel
-from funasr.lm.seq_rnn_lm import SequentialRNNLM
-from funasr.lm.transformer_lm import TransformerLM
+from funasr.train.abs_model import AbsLM
+from funasr.train.abs_model import LanguageModel
+from funasr.models.seq_rnn_lm import SequentialRNNLM
+from funasr.models.transformer_lm import TransformerLM
from funasr.torch_utils.initialize import initialize
from funasr.train.class_choices import ClassChoices
@@ -34,10 +34,14 @@
def build_lm_model(args):
# token_list
- if args.token_list is not None:
- with open(args.token_list) as f:
+ if isinstance(args.token_list, str):
+ with open(args.token_list, encoding="utf-8") as f:
token_list = [line.rstrip() for line in f]
args.token_list = list(token_list)
+ vocab_size = len(token_list)
+ logging.info(f"Vocabulary size: {vocab_size}")
+ elif isinstance(args.token_list, (tuple, list)):
+ token_list = list(args.token_list)
vocab_size = len(token_list)
logging.info(f"Vocabulary size: {vocab_size}")
else:
@@ -47,6 +51,7 @@
lm_class = lm_choices.get_class(args.lm)
lm = lm_class(vocab_size=vocab_size, **args.lm_conf)
+ args.model = args.model if hasattr(args, "model") else "lm"
model_class = model_choices.get_class(args.model)
model = model_class(lm=lm, vocab_size=vocab_size, **args.model_conf)
--
Gitblit v1.9.1