diff --git a/paddlespeech/server/engine/tts/online/onnx/tts_engine.py b/paddlespeech/server/engine/tts/online/onnx/tts_engine.py index 0995a55da..9dd31a08b 100644 --- a/paddlespeech/server/engine/tts/online/onnx/tts_engine.py +++ b/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'] diff --git a/paddlespeech/server/engine/tts/online/python/tts_engine.py b/paddlespeech/server/engine/tts/online/python/tts_engine.py index a46b84bd9..0cfb20354 100644 --- a/paddlespeech/server/engine/tts/online/python/tts_engine.py +++ b/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 diff --git a/paddlespeech/server/engine/tts/paddleinference/tts_engine.py b/paddlespeech/server/engine/tts/paddleinference/tts_engine.py index 20b98fae6..3a6461f8c 100644 --- a/paddlespeech/server/engine/tts/paddleinference/tts_engine.py +++ b/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'] diff --git a/paddlespeech/t2s/exps/syn_utils.py b/paddlespeech/t2s/exps/syn_utils.py index 3d3620cf9..b720ae489 100644 --- a/paddlespeech/t2s/exps/syn_utils.py +++ b/paddlespeech/t2s/exps/syn_utils.py @@ -31,8 +31,8 @@ from paddle.static import InputSpec 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 diff --git a/paddlespeech/t2s/exps/transformer_tts/preprocess.py b/paddlespeech/t2s/exps/transformer_tts/preprocess.py index 2ebd5ecc2..4e82e53ff 100644 --- a/paddlespeech/t2s/exps/transformer_tts/preprocess.py +++ b/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): diff --git a/paddlespeech/t2s/exps/transformer_tts/synthesize_e2e.py b/paddlespeech/t2s/exps/transformer_tts/synthesize_e2e.py index 0cd7d224e..279407b38 100644 --- a/paddlespeech/t2s/exps/transformer_tts/synthesize_e2e.py +++ b/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 diff --git a/paddlespeech/t2s/frontend/__init__.py b/paddlespeech/t2s/frontend/__init__.py index 09caa1bef..a8f77d552 100644 --- a/paddlespeech/t2s/frontend/__init__.py +++ b/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 * diff --git a/paddlespeech/t2s/frontend/en_frontend.py b/paddlespeech/t2s/frontend/en_frontend.py new file mode 100644 index 000000000..81991e0d7 --- /dev/null +++ b/paddlespeech/t2s/frontend/en_frontend.py @@ -0,0 +1 @@ +from .phonectic import English diff --git a/paddlespeech/t2s/frontend/mix_frontend.py b/paddlespeech/t2s/frontend/mix_frontend.py index fb7ea94e7..343747f8a 100644 --- a/paddlespeech/t2s/frontend/mix_frontend.py +++ b/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]) diff --git a/paddlespeech/t2s/frontend/phonectic.py b/paddlespeech/t2s/frontend/phonectic.py index af86d9b80..2112ff4a7 100644 --- a/paddlespeech/t2s/frontend/phonectic.py +++ b/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):