deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
lyuxiang.lx
2024-12-16 09:42:08 +08:00
parent 6b9cebea14
commit 6b5931dc70
2 changed files with 62 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
cosyvoice/cli/frontend.py
View File

@@ -12,6 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from functools import partial
import json
import onnxruntime
import torch
import numpy as np
@@ -66,9 +67,7 @@ class CosyVoiceFrontEnd:
ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
assert self.frd.initialize('{}/../../pretrained_models/CosyVoice-ttsfrd/resource'.format(ROOT_DIR)) is True, \
'failed to initialize ttsfrd resource'
self.frd.set_lang_type('pinyin')
self.frd.enable_pinyin_mix(True)
self.frd.set_breakmodel_index(1)
self.frd.set_lang_type('pinyinvg')
else:
self.zh_tn_model = ZhNormalizer(remove_erhua=False, full_to_half=False)
self.en_tn_model = EnNormalizer()
@@ -112,26 +111,28 @@ class CosyVoiceFrontEnd:
text = text.strip()
if contains_chinese(text):
if self.use_ttsfrd:
text = self.frd.get_frd_extra_info(text, 'input')
texts = [i["text"] for i in json.loads(self.frd.do_voicegen_frd(text))["sentences"]]
text = ''.join(texts)
else:
text = self.zh_tn_model.normalize(text)
text = text.replace("\n", "")
text = replace_blank(text)
text = replace_corner_mark(text)
text = text.replace(".", "。")
text = text.replace(" - ", "，")
text = remove_bracket(text)
text = re.sub(r'[，,、]+$', '。', text)
texts = list(split_paragraph(text, partial(self.tokenizer.encode, allowed_special=self.allowed_special), "zh", token_max_n=80,
token_min_n=60, merge_len=20, comma_split=False))
text = text.replace("\n", "")
text = replace_blank(text)
text = replace_corner_mark(text)
text = text.replace(".", "。")
text = text.replace(" - ", "，")
text = remove_bracket(text)
text = re.sub(r'[，,、]+$', '。', text)
texts = list(split_paragraph(text, partial(self.tokenizer.encode, allowed_special=self.allowed_special), "zh", token_max_n=80,
token_min_n=60, merge_len=20, comma_split=False))
else:
if self.use_ttsfrd:
text = self.frd.get_frd_extra_info(text, 'input')
texts = [i["text"] for i in json.loads(self.frd.do_voicegen_frd(text))["sentences"]]
text = ''.join(texts)
else:
text = self.en_tn_model.normalize(text)
text = spell_out_number(text, self.inflect_parser)
texts = list(split_paragraph(text, partial(self.tokenizer.encode, allowed_special=self.allowed_special), "en", token_max_n=80,
token_min_n=60, merge_len=20, comma_split=False))
text = spell_out_number(text, self.inflect_parser)
texts = list(split_paragraph(text, partial(self.tokenizer.encode, allowed_special=self.allowed_special), "en", token_max_n=80,
token_min_n=60, merge_len=20, comma_split=False))
if split is False:
return text
return texts