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 | 40 ++++++++++++++++++++++++++++++++++------
1 files changed, 34 insertions(+), 6 deletions(-)
diff --git a/funasr/build_utils/build_lm_model.py b/funasr/build_utils/build_lm_model.py
index 2cd869d..f78a20e 100644
--- a/funasr/build_utils/build_lm_model.py
+++ b/funasr/build_utils/build_lm_model.py
@@ -1,6 +1,9 @@
-from funasr.lm.abs_model import AbsLM
-from funasr.lm.seq_rnn_lm import SequentialRNNLM
-from funasr.lm.transformer_lm import TransformerLM
+import logging
+
+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
@@ -13,22 +16,47 @@
type_check=AbsLM,
default="seq_rnn",
)
+model_choices = ClassChoices(
+ "model",
+ classes=dict(
+ lm=LanguageModel,
+ ),
+ default="lm",
+)
class_choices_list = [
# --lm and --lm_conf
- lm_choices
+ lm_choices,
+ # --model and --model_conf
+ model_choices
]
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:
vocab_size = None
+ # lm
+ 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)
+
+ # initialize
+ if args.init is not None:
+ initialize(model, args.init)
+
return model
--
Gitblit v1.9.1