Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.
def translations(
self,
audio: bytes,
prompt: Optional[str] = None,
response_format: Optional[str] = "json",
temperature: Optional[float] = 0,
):
"""
Translates audio into English.
Parameters
----------
audio: bytes
The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg,
mpga, m4a, ogg, wav, or webm.
prompt: Optional[str]
An optional text to guide the model's style or continue a previous audio segment.
The prompt should match the audio language.
response_format: Optional[str], defaults to json
The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
temperature: Optional[float], defaults to 0
The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random,
while lower values like 0.2 will make it more focused and deterministic.
If set to 0, the model will use log probability to automatically increase the temperature
until certain thresholds are hit.
Returns
-------
The translated text.
"""
url = f"{self._base_url}/v1/audio/translations"
params = {
"model": self._model_uid,
"prompt": prompt,
"response_format": response_format,
"temperature": temperature,
}
files: List[Any] = []
for key, value in params.items():
files.append((key, (None, value)))
files.append(("file", ("file", audio, "application/octet-stream")))
response = requests.post(url, files=files, headers=self.auth_headers)
if response.status_code != 200:
raise RuntimeError(
f"Failed to translate the audio, detail: {_get_error_string(response)}"
)
response_data = response.json()
return response_data
openai/whisper-large-v3的翻译xinference是否支持英翻译中?我看底层代码只写了中翻英?是否可以重写参数,如何实现?谢谢