mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
27 lines
807 B
Python
27 lines
807 B
Python
#!/usr/bin/env python3
|
|
# -*- encoding: utf-8 -*-
|
|
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
|
|
# MIT License (https://opensource.org/licenses/MIT)
|
|
|
|
# To install requirements: pip3 install -U "funasr[llm]"
|
|
|
|
from funasr import AutoModel
|
|
|
|
model = AutoModel(model="Qwen/Qwen-Audio-Chat",
|
|
model_path=None,
|
|
)
|
|
|
|
audio_in = "https://github.com/QwenLM/Qwen-Audio/raw/main/assets/audio/1272-128104-0000.flac"
|
|
|
|
# 1st dialogue turn
|
|
prompt = 'what does the person say?'
|
|
cache = {"history": None}
|
|
res = model.generate(input=audio_in, prompt=prompt, cache=cache)
|
|
print(res)
|
|
|
|
prompt = 'Find the start time and end time of the word "middle classes"'
|
|
# 2nd dialogue turn
|
|
res = model.generate(input=None, prompt=prompt, cache=cache)
|
|
print(res)
|
|
|