mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-24 08:03:53 +08:00
更新GPT_SOVITS_V3接口 (#375)
* ollama去除回复中的think字段 (#373) * ollama调用修复，并且去除回复中的think字段（deepseek） * ollama调用修复，并且去除回复中的think字段（deepseek） * ollama去除回复中的think字段（deepseek） deepseek 14b，qwen2.5测试通过 * ollama去除回复中的think字段（deepseek） deepseek 14b，qwen2.5测试通过 * Update ollama.py --------- Co-authored-by: aileenfun <105077614@qq.com> Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com> * fix：GPT_SOVITS_V3-20250228 API (#312) --------- Co-authored-by: aileenfun <alanliu0618@gmail.com> Co-authored-by: aileenfun <105077614@qq.com> Co-authored-by: Miyo <101488652+Miyokiss@users.noreply.github.com>
This commit is contained in:
欣南科技
co-authored by
aileenfun
aileenfun
Miyo
aileenfun
aileenfun
Miyo
parent
490a66d3fe
commit
8376b6f0f2
@@ -306,20 +306,24 @@ TTS:
|
||||
repetition_penalty: 1.35
|
||||
aux_ref_audio_paths: []
|
||||
GPT_SOVITS_V3:
|
||||
# 定义TTS API类型 GPT-SoVITS-v3lora-20250228
|
||||
#启动tts方法：
|
||||
#python api.py
|
||||
type: gpt_sovits_v3
|
||||
url: "http://127.0.0.1:9880/tts"
|
||||
url: "http://127.0.0.1:9880"
|
||||
output_file: tmp/
|
||||
text_lang: "auto"
|
||||
ref_audio_path: "caixukun.wav"
|
||||
prompt_lang: "zh"
|
||||
text_language: "auto"
|
||||
refer_wav_path: "caixukun.wav"
|
||||
prompt_language: "zh"
|
||||
prompt_text: ""
|
||||
top_k: 5
|
||||
top_p: 1
|
||||
temperature: 1
|
||||
sample_steps: 16
|
||||
media_type: "wav"
|
||||
streaming_mode: false
|
||||
threshold: 30
|
||||
top_k: 15
|
||||
top_p: 1.0
|
||||
temperature: 1.0
|
||||
cut_punc: ""
|
||||
speed: 1.0
|
||||
inp_refs: []
|
||||
sample_steps: 32
|
||||
if_sr: false
|
||||
MinimaxTTS:
|
||||
# Minimax语音合成服务，需要先在minimax平台创建账户充值，并获取登录信息
|
||||
# 平台地址：https://platform.minimaxi.com/
|
||||
|
||||
@@ -12,10 +12,10 @@ class LLMProvider(LLMProviderBase):
|
||||
self.model_name = config.get("model_name")
|
||||
self.base_url = config.get("base_url", "http://localhost:11434")
|
||||
# Initialize OpenAI client with Ollama base URL
|
||||
#如果没有v1，增加v1
|
||||
# 如果没有v1，增加v1
|
||||
if not self.base_url.endswith("/v1"):
|
||||
self.base_url = f"{self.base_url}/v1"
|
||||
|
||||
|
||||
self.client = OpenAI(
|
||||
base_url=self.base_url,
|
||||
api_key="ollama" # Ollama doesn't need an API key but OpenAI client requires one
|
||||
@@ -28,13 +28,20 @@ class LLMProvider(LLMProviderBase):
|
||||
messages=dialogue,
|
||||
stream=True
|
||||
)
|
||||
|
||||
is_active=True
|
||||
for chunk in responses:
|
||||
try:
|
||||
delta = chunk.choices[0].delta if getattr(chunk, 'choices', None) else None
|
||||
content = delta.content if hasattr(delta, 'content') else ''
|
||||
if content:
|
||||
yield content
|
||||
if '<think>' in content:
|
||||
is_active = False
|
||||
content = content.split('<think>')[0]
|
||||
if '</think>' in content:
|
||||
is_active = True
|
||||
content = content.split('</think>')[-1]
|
||||
if is_active:
|
||||
yield content
|
||||
except Exception as e:
|
||||
logger.bind(tag=TAG).error(f"Error processing chunk: {e}")
|
||||
|
||||
@@ -50,10 +57,10 @@ class LLMProvider(LLMProviderBase):
|
||||
stream=True,
|
||||
tools=functions,
|
||||
)
|
||||
|
||||
|
||||
for chunk in stream:
|
||||
yield chunk.choices[0].delta.content, chunk.choices[0].delta.tool_calls
|
||||
|
||||
except Exception as e:
|
||||
logger.bind(tag=TAG).error(f"Error in Ollama function call: {e}")
|
||||
yield {"type": "content", "content": f"【Ollama服务响应异常: {str(e)}】"}
|
||||
yield {"type": "content", "content": f"【Ollama服务响应异常: {str(e)}】"}
|
||||
|
||||
@@ -12,17 +12,18 @@ class TTSProvider(TTSProviderBase):
|
||||
def __init__(self, config, delete_audio_file):
|
||||
super().__init__(config, delete_audio_file)
|
||||
self.url = config.get("url")
|
||||
self.text_lang = config.get("text_lang", "audo")
|
||||
self.ref_audio_path = config.get("ref_audio_path")
|
||||
self.prompt_lang = config.get("prompt_lang")
|
||||
self.refer_wav_path = config.get("refer_wav_path")
|
||||
self.prompt_text = config.get("prompt_text")
|
||||
self.top_k = config.get("top_k", 5)
|
||||
self.top_p = config.get("top_p", 1)
|
||||
self.temperature = config.get("temperature", 1)
|
||||
self.sample_steps = config.get("sample_steps", 16)
|
||||
self.media_type = config.get("media_type", "wav")
|
||||
self.streaming_mode = config.get("streaming_mode", False)
|
||||
self.threshold = config.get("threshold", 30)
|
||||
self.prompt_language = config.get("prompt_language")
|
||||
self.text_language = config.get("text_language", "audo")
|
||||
self.top_k = config.get("top_k", 15)
|
||||
self.top_p = config.get("top_p", 1.0)
|
||||
self.temperature = config.get("temperature", 1.0)
|
||||
self.cut_punc = config.get("cut_punc","")
|
||||
self.speed = config.get("speed", 1.0)
|
||||
self.inp_refs = config.get("inp_refs",[])
|
||||
self.sample_steps = config.get("inp_refs",32)
|
||||
self.if_sr = config.get("if_sr",False)
|
||||
|
||||
|
||||
def generate_filename(self, extension=".wav"):
|
||||
@@ -30,18 +31,19 @@ class TTSProvider(TTSProviderBase):
|
||||
|
||||
async def text_to_speak(self, text, output_file):
|
||||
request_params = {
|
||||
"text": text,
|
||||
"text_lang": self.text_lang,
|
||||
"ref_audio_path": self.ref_audio_path,
|
||||
"prompt_lang": self.prompt_lang,
|
||||
"refer_wav_path": self.refer_wav_path,
|
||||
"prompt_text": self.prompt_text,
|
||||
"prompt_language": self.prompt_language,
|
||||
"text": text,
|
||||
"text_language": self.text_language,
|
||||
"top_k": self.top_k,
|
||||
"top_p": self.top_p,
|
||||
"temperature": self.temperature,
|
||||
"cut_punc": self.cut_punc,
|
||||
"speed": self.speed,
|
||||
"inp_refs": self.inp_refs,
|
||||
"sample_steps": self.sample_steps,
|
||||
"media_type": self.media_type,
|
||||
"streaming_mode": self.streaming_mode,
|
||||
"threshold": self.threshold,
|
||||
"if_sr": self.if_sr,
|
||||
}
|
||||
|
||||
resp = requests.get(self.url, params=request_params)
|
||||
|
||||
Reference in New Issue
Block a user