class ASR():
def __init__(self, am_config, lm_config):
self.am = AM(am_config)
self.am.load_model(False)
self.lm = LM(lm_config)
self.lm.load_model(False)
def decode_am_result(self, result):
return self.am.decode_result(result)
def stt(self, wav_path):
am_result = self.am.predict(wav_path)
if self.am.model_type == 'Transducer':
am_result = self.decode_am_result(am_result[1:-1])
lm_result = self.lm.predict(am_result)
lm_result = self.lm.decode(lm_result[0].numpy(),
self.lm.lm_featurizer)
else:
am_result = self.decode_am_result(am_result[0])
lm_result = self.lm.predict(am_result)
lm_result = self.lm.decode(lm_result[0].numpy(),
self.lm.lm_featurizer)
return am_result, lm_result
def am_test(self, wav_path):
# am_result is token id
am_result = self.am.predict(wav_path)
# token to vocab
if self.am.model_type == 'Transducer':
am_result = self.decode_am_result(am_result[1:-1])
else:
am_result = self.decode_am_result(am_result[0])
return am_result
def lm_test(self, txt):
if self.lm.config['am_token']['for_multi_task']:
pys = pypinyin.pinyin(txt, 8, neutral_tone_with_five=True)
input_py = [i[0] for i in pys]
else:
pys = pypinyin.pinyin(txt)
input_py = [i[0] for i in pys]
# now lm_result is token id
lm_result = self.lm.predict(input_py)
# token to vocab
lm_result = self.lm.decode(lm_result[0].numpy(), self.lm.lm_featurizer)
return lm_result
class ASR():
def __init__(self, am_config):
self.am = AM(am_config)
self.am.load_model(False)
def decode_am_result(self, result):
return self.am.decode_result(result)
def am_test(self, wav_path):
# am_result is token id
am_result = self.am.predict(wav_path)
# token to vocab
if self.am.model_type == 'Transducer':
am_result = self.decode_am_result(am_result[1:-1])
else:
am_result = self.decode_am_result(am_result[0])
return am_result
class ASR():
def __init__(self, am_config, lm_config):
self.am = AM(am_config)
self.am.load_model(False)
self.lm = LM(lm_config)
self.lm.load_model()
def decode_am_result(self, result):
return self.am.decode_result(result[0])
def stt(self, wav_path):
am_result = self.am.predict(wav_path)
lm_result = self.lm.predict(self.decode_am_result(am_result))
return am_result, lm_result
