gyt/opendan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

story maker

Browse Source
This commit is contained in:
wugren
2023-09-21 15:52:56 +08:00
parent 270debef67
commit 4e45130140
10 changed files with 341 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/aios_kernel/google_text_to_speech_node.py
+70 -11
View File
@@ -21,24 +21,69 @@ see:https://cloud.google.com/text-to-speech/docs/before-you-begin
class GoogleTextToSpeechNode(ComputeNode):
_instance = None
def __new__(cls, *args, **kwargs):
@classmethod
def get_instance(cls):
if cls._instance is None:
cls._instance = super(GoogleTextToSpeechNode, cls).__new__(cls)
cls._instance.is_start = False
cls._instance = cls()
return cls._instance
def __init__(self):
super().__init__()
if self.is_start is True:
logger.warn("GoogleTextToSpeechNode is already start")
return
self.is_start = True
self.node_id = "google_text_to_speech_node"
self.task_queue = Queue()
self.client = texttospeech.TextToSpeechClient()
self.language_list = {
"cnm-CN": {
"female": ["cmn-CN-Standard-A",
"cmn-CN-Standard-D",
"cmn-CN-Wavenet-A",
"cmn-CN-Wavenet-D",
"cmn-TW-Standard-A",
"cmn-TW-Wavenet-A"],
"man": ["cmn-CN-Standard-B",
"cmn-CN-Standard-C",
"cmn-CN-Wavenet-B",
"cmn-CN-Wavenet-C",
"cmn-TW-Standard-B",
"cmn-TW-Standard-C",
"cmn-TW-Wavenet-B",
"cmn-TW-Wavenet-C"]
},
"en-US": {
"female": ["en-US-Neural2-C",
"en-US-Neural2-E",
"en-US-Neural2-F",
"en-US-Neural2-G",
"en-US-Neural2-H",
"en-US-News-K",
"en-US-News-L",
"en-US-Standard-C",
"en-US-Standard-E",
"en-US-Standard-F",
"en-US-Standard-G",
"en-US-Standard-H",
"en-US-Studio-O",
"en-US-Wavenet-C",
"en-US-Wavenet-E",
"en-US-Wavenet-F",
"en-US-Wavenet-G",
"en-US-Wavenet-H"],
"man": ["en-US-Polyglot-1",
"en-US-Standard-A",
"en-US-Standard-B",
"en-US-Standard-D",
"en-US-Standard-I",
"en-US-Standard-J",
"en-US-Studio-M",
"en-US-Wavenet-A",
"en-US-Wavenet-B",
"en-US-Wavenet-D",
"en-US-Wavenet-I",
"en-US-Wavenet-J"]
}
}
self.start()
def start(self):
@@ -64,10 +109,24 @@ class GoogleTextToSpeechNode(ComputeNode):
task.state = ComputeTaskState.RUNNING
language_code = task.params["language_code"]
text = task.params["text"]
voice_name = task.params["voice_name"]
gender = task.params["gender"]
age = task.params["age"]
if language_code == "zh":
language_code = "cnm-CN"
elif language_code == "en":
language_code = "en-US"
else:
raise Exception(f"language_code {language_code} not support")
lang_list = self.language_list[language_code][gender]
voice = lang_list[hash(voice_name) % len(lang_list)]
synthesis_input = texttospeech.SynthesisInput(text=text)
voice = texttospeech.VoiceSelectionParams(language_code=language_code,
ssml_gender=texttospeech.SsmlVoiceGender.NEUTRAL)
ssml_gender=texttospeech.SsmlVoiceGender.NEUTRAL,
name=voice)
audio_config = texttospeech.AudioConfig(audio_encoding=texttospeech.AudioEncoding.MP3)
@@ -95,8 +154,8 @@ class GoogleTextToSpeechNode(ComputeNode):
def get_capacity(self):
return 0
def is_support(self, task_type: ComputeTaskType) -> bool:
if task_type == ComputeTaskType.TEXT_2_VOICE:
def is_support(self, task: ComputeTask) -> bool:
if task.task_type == ComputeTaskType.TEXT_2_VOICE:
return True
return False