我用阿里最有诚意的开源，拼成了开源的GPT-4o 之一

在看了阿里最有诚意的开源项目：FunAudioLLM 我就有了个想法，为什么不把它搞成个语音入，语音出的家伙呢？

这样，也许我就有了J.A.R.V.I.S 的基础部分，语音对话能力。因为FunAudioLLM提供了语音输入与语音输出两个模型(输出还提供声音定制能力)。

大脑，也有啊，阿里的另一个诚意开源项目QWen2，也是开源模型里能打的扛把子啊。

于是，你看，下面这东西是不是很完美？

实际效果我们看看吧，它是一个完全基于Web的版本，当然了，如果你愿意改成其它类型的App也不是啥难事。反正现在有GPT一类的助手，Wrap一个App也是很轻松的事！

给你个最终的生成结果声音听一下：

安装

这个过程也没有想象的那么麻烦，安装三个基础模型的运行环境。

第一个我选择了 CosyVoice

其实是可以完全按官方提供的说明进行安装与配置的，不过你要考虑国内的环境问题，可能有一些要特殊处理。

#下面这几步居然需要魔法了，你敢信？？？？？程序员得罪谁了？gitclone--recursivehttps://github.com/FunAudioLLM/CosyVoice.git#Ifyoufailedtoclonesubmoduleduetonetworkfailures,pleaserunfollowingcommanduntilsuccesscdCosyVoicegitsubmoduleupdate--init--recursive

安装conda这事不用说了，如果你不会用conda，那你大概率也不会看到这篇文章吧。

接来来假设你用的是Ubuntu系统，我的是22.04

conda create -n cosyvoice python=3.8conda activate cosyvoice# pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platform.conda install -y -c conda-forge pynini==2.1.5pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
# If you encounter sox compatibility issues# ubuntusudo apt-get install sox libsox-dev

到这儿，环境肯定是安装完了。下载模型吧，国内的modescope提供的下载镜像真的是快啊。

你可以运行python命令，然后在python的交互过程中执行下面的python代码。

# SDK模型下载from modelscope import snapshot_downloadsnapshot_download('iic/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')snapshot_download('iic/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')snapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')snapshot_download('iic/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')

测试一下

export PYTHONPATH=third_party/Matcha-TTS #这一步很重要
下面的代码存成个python文件，就可以直接测试执行一下了。

from cosyvoice.cli.cosyvoice import CosyVoicefrom cosyvoice.utils.file_utils import load_wavimport torchaudio
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT')# sft usageprint(cosyvoice.list_avaliable_spks())output = cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女')torchaudio.save('sft.wav', output['tts_speech'], 22050)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M')# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Koreanprompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)output = cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k)torchaudio.save('zero_shot.wav', output['tts_speech'], 22050)# cross_lingual usageprompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)output = cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k)torchaudio.save('cross_lingual.wav', output['tts_speech'], 22050)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]output = cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.')torchaudio.save('instruct.wav', output['tts_speech'], 22050)

如果你能顺利得到几个生成的音频文件，那就说明你成功了一大半了。

第二个是SenseVoice

如果你顺利了使用了CosyVoice，那下面这操作的就很简单了。

git clone https://github.com/FunAudioLLM/SenseVoice.git cd SenseVoicepip install -r requirements.txt #如果你想快一点儿，可以加上 -i https://pypi.tuna.tsinghua.edu.cn/simple

接下来执行下面的测试代码

from model import SenseVoiceSmall
model_dir = "iic/SenseVoiceSmall"m, kwargs = SenseVoiceSmall.from_pretrained(model=model_dir)

res = m.inference(data_in="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",language="zh", # "zn", "en", "yue", "ja", "ko", "nospeech"use_itn=False,**kwargs,)
print(res)

如果能正常执行，你会得到一个输出如下：

([{'key':'wav_file_tmp_name','text':'<|zh|><|NEUTRAL|><|Speech|><|woitn|>欢迎大家来体验打摩院推出的语音识别模型'}],{'load_data':'0.338','extract_feat':'0.020','batch_data_time':5.58})

第三个是Ollama + Qwen2

现在你已经验证了可以正常获得STT与TTS了。接下来自然是大脑Qwen2了。考虑到做成服务的便捷与可替换性，我们选择了个比较流行的LLM服务框架：Ollama。这是一个专门运行llama一系列的服务。

#linux为主的一个安装方法，前提你已经安装好了nvidia的一系列驱动了。
sudo curl -L https://ollama.com/download/ollama-linux-amd64 -o /usr/bin/ollamasudo chmod +x /usr/bin/ollamasudo useradd -r -s /bin/false -m -d /usr/share/ollama ollama
#编辑一个下面的文件：/etc/systemd/system/ollama.service
[Unit]Description=Ollama ServiceAfter=network-online.target
[Service]ExecStart=/usr/bin/ollama serveUser=ollamaGroup=ollamaRestart=alwaysRestartSec=3
[Install]WantedBy=default.target
#再执行下面的服务命令，重新启动与设置一下服务
sudo systemctl daemon-reloadsudo systemctl enable ollama
#再启动一下
sudo systemctl start ollama
#再运行一下 ollama 执行特定的模型，好了，你就能进入到一个简单的对话界面。如果好用了，就是好用了。
ollama run qwen2:7b

现在你可以确认，所有的基础部件都完成了安装了！

接口调用

我写了个简单的python文件，把它们都调用了一下。

import sys
sys.path.append("/data/home/todo/SenseVoice") sys.path.append("/data/home/todo/CosyVoice") import requestsfrom model import SenseVoiceSmallfrom cosyvoice.cli.cosyvoice import CosyVoiceimport torchaudio
# Paths and URLsaudio_file_path = "/data/home/todo/aliAllInOne/asr_example_zh.wav"# Replace with the path to your audio fileollama_url = "http://localhost:11434/api/generate"cosyvoice_model_path = '/data/home/todo/CosyVoice/pretrained_models/CosyVoice-300M-SFT'generated_audio_path = "/data/home/todo/aliAllInOne/generated_audio.wav"
# Load the SenseVoiceSmall modelmodel_dir = "iic/SenseVoiceSmall"model_dir = "/home/todo/.cache/modelscope/hub/iic/SenseVoiceSmall"m, kwargs = SenseVoiceSmall.from_pretrained(model=model_dir)
# Step 1: Perform inference using SenseVoiceSmalldef call_sense_voice_small(audio_path, language="zh"):res = m.inference(data_in=audio_path,language=language,use_itn=False,**kwargs,)return res[0][0]['text']#return res
# Step 2: Call the Ollama servicedef call_ollama_service(content):response = requests.post(ollama_url,json={"model": "qwen2:7b","prompt": content,"format": "json", "stream": False})print(response)print(response.status_code, type(response.status_code))if response.status_code == 200:return response.json()["response"]else:return "Error: Unable to get response from Ollama service."
# Step 3: Generate speech using CosyVoicedef generate_speech_with_cosyvoice(text, speaker="中文女"):cosyvoice = CosyVoice(cosyvoice_model_path)output = cosyvoice.inference_sft(text, speaker)torchaudio.save(generated_audio_path, output['tts_speech'], 22050)
# Main function to execute the stepsdef main():# Step 1: Call SenseVoiceSmallsense_voice_result = call_sense_voice_small(audio_file_path)print("SenseVoiceSmall Result:", sense_voice_result)
# Step 2: Call Ollama Serviceollama_result = call_ollama_service(sense_voice_result)print("Ollama Service Result:", ollama_result)
# Step 3: Generate and save the speechgenerate_speech_with_cosyvoice(ollama_result)print(f"Generated audio saved to {generated_audio_path}")
if __name__ == "__main__":main()

你那生成的语音是什么呢？下面的是我的程序生成的！

界面

交给你自己完成吧，毕竟我也搞了一个基础了嘛。