add en_frontend file

paddlespeech/server/engine/tts/online/onnx/tts_engine.py

@@ -28,7 +28,7 @@ from paddlespeech.server.utils.audio_process import float2pcm
 from paddlespeech.server.utils.onnx_infer import get_sess
 from paddlespeech.server.utils.util import denorm
 from paddlespeech.server.utils.util import get_chunks
-from paddlespeech.t2s.frontend import English
+from paddlespeech.t2s.frontend.en_frontend import English
 from paddlespeech.t2s.frontend.zh_frontend import Frontend
 
 __all__ = ['TTSEngine', 'PaddleTTSConnectionHandler']

paddlespeech/server/engine/tts/online/python/tts_engine.py

@@ -29,7 +29,7 @@ from paddlespeech.server.engine.base_engine import BaseEngine
 from paddlespeech.server.utils.audio_process import float2pcm
 from paddlespeech.server.utils.util import denorm
 from paddlespeech.server.utils.util import get_chunks
-from paddlespeech.t2s.frontend import English
+from paddlespeech.t2s.frontend.en_frontend import English
 from paddlespeech.t2s.frontend.zh_frontend import Frontend
 from paddlespeech.t2s.modules.normalizer import ZScore
 

paddlespeech/server/engine/tts/paddleinference/tts_engine.py

@@ -32,7 +32,7 @@ from paddlespeech.server.utils.errors import ErrorCode
 from paddlespeech.server.utils.exception import ServerBaseException
 from paddlespeech.server.utils.paddle_predictor import init_predictor
 from paddlespeech.server.utils.paddle_predictor import run_model
-from paddlespeech.t2s.frontend import English
+from paddlespeech.t2s.frontend.en_frontend import English
 from paddlespeech.t2s.frontend.zh_frontend import Frontend
 
 __all__ = ['TTSEngine', 'PaddleTTSConnectionHandler']

paddlespeech/t2s/exps/syn_utils.py

@@ -33,8 +33,8 @@ from yacs.config import CfgNode
 from paddlespeech.t2s.datasets.am_batch_fn import *
 from paddlespeech.t2s.datasets.data_table import DataTable
 from paddlespeech.t2s.datasets.vocoder_batch_fn import Clip_static
-from paddlespeech.t2s.frontend import English
 from paddlespeech.t2s.frontend.canton_frontend import CantonFrontend
+from paddlespeech.t2s.frontend.en_frontend import English
 from paddlespeech.t2s.frontend.mix_frontend import MixFrontend
 from paddlespeech.t2s.frontend.sing_frontend import SingFrontend
 from paddlespeech.t2s.frontend.zh_frontend import Frontend

paddlespeech/t2s/exps/transformer_tts/preprocess.py

@@ -27,7 +27,7 @@ import yaml
 from yacs.config import CfgNode as Configuration
 
 from paddlespeech.t2s.datasets.get_feats import LogMelFBank
-from paddlespeech.t2s.frontend import English
+from paddlespeech.t2s.frontend.en_frontend import English
 
 
 def get_lj_sentences(file_name, frontend):

paddlespeech/t2s/exps/transformer_tts/synthesize_e2e.py

@@ -21,7 +21,7 @@ import soundfile as sf
 import yaml
 from yacs.config import CfgNode
 
-from paddlespeech.t2s.frontend import English
+from paddlespeech.t2s.frontend.en_frontend import English
 from paddlespeech.t2s.models.transformer_tts import TransformerTTS
 from paddlespeech.t2s.models.transformer_tts import TransformerTTSInference
 from paddlespeech.t2s.models.waveflow import ConditionalWaveFlow

paddlespeech/t2s/frontend/__init__.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 from .generate_lexicon import *
 from .normalizer import *
-from .phonectic import *
 from .punctuation import *
 from .ssml import *
 from .tone_sandhi import *

paddlespeech/t2s/frontend/en_frontend.py

+from .phonectic import English

paddlespeech/t2s/frontend/mix_frontend.py

@@ -18,9 +18,9 @@ from typing import List
 import numpy as np
 import paddle
 
-from paddlespeech.t2s.frontend import English
+from paddlespeech.t2s.frontend.en_frontend import EnFrontend
 from paddlespeech.t2s.frontend.ssml.xml_processor import MixTextProcessor
-from paddlespeech.t2s.frontend.zh_frontend import Frontend
+from paddlespeech.t2s.frontend.zh_frontend import ZhFrontend
 
 
 class MixFrontend():
@@ -29,9 +29,9 @@ class MixFrontend():
                  phone_vocab_path=None,
                  tone_vocab_path=None):
 
-        self.zh_frontend = Frontend(
+        self.zh_frontend = ZhFrontend(
             phone_vocab_path=phone_vocab_path, tone_vocab_path=tone_vocab_path)
-        self.en_frontend = English(phone_vocab_path=phone_vocab_path)
+        self.en_frontend = EnFrontend(phone_vocab_path=phone_vocab_path)
         self.sp_id = self.zh_frontend.vocab_phones["sp"]
         self.sp_id_numpy = np.array([self.sp_id])
         self.sp_id_tensor = paddle.to_tensor([self.sp_id])

paddlespeech/t2s/frontend/phonectic.py

@@ -86,8 +86,8 @@ class English(Phonetics):
                       sentence: str,
                       merge_sentences: bool=False,
                       to_tensor: bool=True) -> paddle.Tensor:
-        result = {}
         sentences = self.text_normalizer._split(sentence, lang="en")
+
         phones_list = []
         temp_phone_ids = []
         for sentence in sentences:
@@ -118,7 +118,10 @@ class English(Phonetics):
             if to_tensor:
                 phone_ids = paddle.to_tensor(phone_ids)
             temp_phone_ids.append(phone_ids)
+
+        result = {}
         result["phone_ids"] = temp_phone_ids
+
         return result
 
     def numericalize(self, phonemes):