智谱语音识别大模型开源，支持中国方言，消费级显卡本地部署

pip install -r requirements.txt
sudo apt install ffmpeg

pip install git+https://github.com/huggingface/transformers

from transformers import AutoModel, AutoProcessor
import torch
device = "cuda"if torch.cuda.is_available() else"cpu"
repo_id = "zai-org/GLM-ASR-Nano-2512"
processor = AutoProcessor.from_pretrained(repo_id)
model = AutoModel.from_pretrained(repo_id, dtype=torch.bfloat16, device_map=device)
messages = [
{
"role": "user",
"content": [
{
"type": "audio",
"url": "example_zh.wav",
},
{"type": "text", "text": "Please transcribe this audio into text"},
],
}
]
inputs = processor.apply_chat_template(
messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt"
)
inputs = inputs.to(device, dtype=torch.bfloat16)
outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)
print(processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True))

python -m vllm.entrypoints.openai.api_server --model /data/models/GLM-ASR-Nan0-2512 
--trust-remote-code  
--dtype bfloat16   
--host 0.0.0.0 
--port 8000

from openai import OpenAI
# Modify with the actual server address
client = OpenAI(base_url="http://localhost:8000/v1", api_key="dummy")
# Transcribe audio file
with open("audio.mp3", "rb") as audio_file:
transcript = client.audio.transcriptions.create(
model="GLM-ASR-Nano-2512",
file=audio_file
)
print(transcript.text)

# 拉取开发版docker镜像
docker pull lmsysorg/sglang:dev
# 进入容器后运行
pip install git+https://github.com/huggingface/transformers
python3 -m sglang.launch_server --model-path zai-org/GLM-ASR-Nano-2512 --served-model-name glm-asr --host 0.0.0.0 --port 8000

from openai import OpenAI
openai_api_key = "EMPTY"
openai_api_base = "http://127.0.0.1:8000/v1"
client = OpenAI(api_key=openai_api_key, base_url=openai_api_base)
response = client.chat.completions.create(
model="glm-asr",
messages=[
{
"role": "user",
"content": [
{
"type": "audio_url",
"audio_url": {"url": "example_zh.wav"}
},
{
"type": "text",
"text": "Please transcribe this audio into text"
},
]
}
],
max_tokens=1024,
)
print(response.choices[0].message.content.strip())

from transformers import GlmAsrForConditionalGeneration, AutoProcessor
processor = AutoProcessor.from_pretrained("zai-org/GLM-ASR-Nano-2512")
model = GlmAsrForConditionalGeneration.from_pretrained("zai-org/GLM-ASR-Nano-2512", dtype="auto", device_map="auto")
inputs = processor.apply_transcription_request([
"audio1.mp3",
"audio2.mp3",
])
inputs = inputs.to(model.device, dtype=model.dtype)
outputs = model.generate(**inputs, do_sample=False, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(decoded_outputs)