* Relax version requirements in audio.txt

* Fix bugs in ttsfrd which may cause text-to-speech break disappear and upgrade it to version 0.0.2
* other fix to make ut pass

modelscope/models/audio/tts/am/sambert_hifi_16k.py

@@ -18,7 +18,7 @@ __all__ = ['SambertNetHifi16k']
 
 
 def multi_label_symbol_to_sequence(my_classes, my_symbol):
-    one_hot = MultiLabelBinarizer(my_classes)
+    one_hot = MultiLabelBinarizer(classes=my_classes)
     tokens = my_symbol.strip().split(' ')
     sequences = []
     for token in tokens:

modelscope/models/audio/tts/frontend/generic_text_to_speech_frontend.py

@@ -20,7 +20,6 @@ class GenericTtsFrontend(Model):
     def __init__(self, model_dir='.', lang_type='pinyin', *args, **kwargs):
         super().__init__(model_dir, *args, **kwargs)
         import ttsfrd
-
         frontend = ttsfrd.TtsFrontendEngine()
         zip_file = os.path.join(model_dir, 'resource.zip')
         self._res_path = os.path.join(model_dir, 'resource')

requirements/audio.txt

@@ -1,25 +1,25 @@
 #tts
-h5py==2.10.0
-https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/ttsfrd-0.0.1-cp36-cp36m-linux_x86_64.whl; python_version=='3.6'
-https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/ttsfrd-0.0.1-cp37-cp37m-linux_x86_64.whl; python_version=='3.7'
-https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/ttsfrd-0.0.1-cp38-cp38-linux_x86_64.whl; python_version=='3.8'
-https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/ttsfrd-0.0.1-cp39-cp39-linux_x86_64.whl; python_version=='3.9'
-https://swap.oss-cn-hangzhou.aliyuncs.com/Jiaqi%2Fmaas%2Ftts%2Frequirements%2Fpytorch_wavelets-1.3.0-py3-none-any.whl?Expires=1685688388&OSSAccessKeyId=LTAI4Ffebq4d9jTVDwiSbY4L&Signature=jcQbg5EZ%2Bdys3%2F4BRn3srrKLdIg%3D
+h5py
+https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/pytorch_wavelets-1.3.0-py3-none-any.whl
+https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/ttsfrd-0.0.2-cp36-cp36m-linux_x86_64.whl; python_version=='3.6'
+https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/ttsfrd-0.0.2-cp37-cp37m-linux_x86_64.whl; python_version=='3.7'
+https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/ttsfrd-0.0.2-cp38-cp38-linux_x86_64.whl; python_version=='3.8'
+https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/requirements/ttsfrd-0.0.2-cp39-cp39-linux_x86_64.whl; python_version=='3.9'
 inflect
-keras==2.2.4
+keras
 librosa
 lxml
 matplotlib
 nara_wpe
-numpy==1.18.*
+numpy
 protobuf>3,<=3.20
 ptflops
 PyWavelets>=1.0.0
-scikit-learn==0.23.2
+scikit-learn
 sox
 tensorboard
 tensorflow==1.15.*
-torch==1.10.*
+torch
 torchaudio
 torchvision
 tqdm