from PyAnnote.audio import Pipeline

def model_fn(model_dir):
# Load the model from the specified model directory
model = Pipeline.from_pretrained(
"PyAnnote/speaker-diarization-3.1",
use_auth_token="Replace-with-the-Hugging-face-auth-token")
return model

with open("model/code/requirements.txt", "w") as f:
    f.write("transformers==4.25.1n")
    f.write("boto3n")
    f.write("PyAnnote.audion")
    f.write("soundfilen")
    f.write("librosan")
    f.write("onnxruntimen")
    f.write("wgetn")
    f.write("pandas")

!tar zcvf model.tar.gz *

import sagemaker
import boto3

sess = sagemaker.Session()

sagemaker_session_bucket = None
if sagemaker_session_bucket is None and sess is not None:
    sagemaker_session_bucket = sess.default_bucket()

try:
    role = sagemaker.get_execution_role()
except ValueError:
    iam = boto3.client("iam")
    role = iam.get_role(RoleName="sagemaker_execution_role")["Role"]["Arn"]

sess = sagemaker.Session(default_bucket=sagemaker_session_bucket)

print(f"sagemaker role arn: {role}")
print(f"sagemaker bucket: {sess.default_bucket()}")
print(f"sagemaker session region: {sess.boto_region_name}")

s3_location = f"s3://{sagemaker_session_bucket}/whisper/model/model.tar.gz"
!aws s3 cp model.tar.gz $s3_location

from sagemaker.huggingface.model import HuggingFaceModel
from sagemaker.async_inference.async_inference_config import AsyncInferenceConfig
from sagemaker.s3 import s3_path_join
from sagemaker.utils import name_from_base

async_endpoint_name = name_from_base("custom-asyc")

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
    model_data=s3_location,  # path to your model and script
    role=role,  # iam role with permissions to create an Endpoint
    transformers_version="4.17",  # transformers version used
    pytorch_version="1.10",  # pytorch version used
    py_version="py38",  # python version used
)

# create async endpoint configuration
async_config = AsyncInferenceConfig(
    output_path=s3_path_join(
        "s3://", sagemaker_session_bucket, "async_inference/output"
    ),  # Where our results will be stored
    # Add nofitication SNS if needed
    notification_config={
        # "SuccessTopic": "PUT YOUR SUCCESS SNS TOPIC ARN",
        # "ErrorTopic": "PUT YOUR ERROR SNS TOPIC ARN",
    },  #  Notification configuration
)

env = {"MODEL_SERVER_WORKERS": "2"}

# deploy the endpoint endpoint
async_predictor = huggingface_model.deploy(
    initial_instance_count=1,
    instance_type="ml.xx",
    async_inference_config=async_config,
    endpoint_name=async_endpoint_name,
    env=env,
)

# Replace with a path to audio object in S3
from sagemaker.async_inference import WaiterConfig
res = async_predictor.predict_async(data=data)
print(f"Response output path: {res.output_path}")
print("Start Polling to get response:")

config = WaiterConfig(
  max_attempts=10, #  number of attempts
  delay=10#  time in seconds to wait between attempts
  )
res.get_result(config)
#import waiterconfig

[0.9762308998, 8.9049235993, "SPEAKER_01"]

[9.533106961, 12.1646859083, "SPEAKER_01"]

[13.1324278438, 13.9303904924, "SPEAKER_00"]

[14.3548387097, 26.1884550085, "SPEAKER_00"]

[27.2410865874, 28.2258064516, "SPEAKER_01"]

[28.3446519525, 31.298811545, "SPEAKER_01"]

# Common class representing application autoscaling for SageMaker 
client = boto3.client('application-autoscaling') 

# This is the format in which application autoscaling references the endpoint
resource_id='endpoint/' + <endpoint_name> + '/variant/' + <'variant1'> 

# Define and register your endpoint variant
response = client.register_scalable_target(
    ServiceNamespace='sagemaker', 
    ResourceId=resource_id,
    ScalableDimension='sagemaker:variant:DesiredInstanceCount', # The number of EC2 instances for your Amazon SageMaker model endpoint variant.
    MinCapacity=0,
    MaxCapacity=5
)

Uma ufuna ukususa iphoyinti lokugcina, sebenzisa ikhodi elandelayo:

async_predictor.delete_endpoint(async_endpoint_name)

Izinzuzo zokuthunyelwa kwephoyinti lokugcina elingavumelanisiwe

Lesi sixazululo sinikeza izinzuzo ezilandelayo:

• Isixazululo singaphatha kahle amafayela omsindo amaningi noma amakhulu.
• Lesi sibonelo sisebenzisa isibonelo esisodwa ukuze sibonise. Uma ufuna ukusebenzisa lesi sixazululo kumakhulu noma izinkulungwane zamavidiyo futhi usebenzise isiphetho esingavumelaniyo ukucubungula ezimweni eziningi, ungasebenzisa inqubomgomo yokukala ngokuzenzakalelayo, eyenzelwe inani elikhulu lamadokhumenti omthombo. Ukukala okuzenzakalelayo kulungisa inani lezimo ezilungiselelwe imodeli ukuphendula izinguquko emthwalweni wakho wokusebenza.
• Isixazululo sithuthukisa izinsiza futhi sinciphise umthwalo wesistimu ngokuhlukanisa imisebenzi ehlala isikhathi eside kusukela ekuqondeni kwesikhathi sangempela.

Isiphetho

Kulokhu okuthunyelwe, sinikeze indlela eqondile yokusebenzisa imodeli yesipikha se-Hugging Face ku-SageMaker sisebenzisa imibhalo yePython. Ukusebenzisa i-asynchronous endpoint kunikeza izindlela ezisebenza kahle nezilinganisekayo zokuletha izibikezelo zokudayela njengesevisi, ezivumela izicelo ezihambisanayo ngaphandle komthungo.

Qalisa namuhla ngokudayela kwe-asynchronous speaker kumaphrojekthi akho omsindo. Finyelela kumazwana uma unemibuzo mayelana nokuthola eyakho i-asynchronous diarization endpoint esebenzayo.

Mayelana Ababhali

Sanjay Tiwary i-Specialist Solutions Architect i-AI/ML echitha isikhathi sayo esebenza namakhasimende anamasu ukuze ichaze izidingo zebhizinisi, inikeze amaseshini e-L300 mayelana nezimo ezithile zokusetshenziswa, futhi iklame izinhlelo zokusebenza ze-AI/ML nezinsizakalo ezingaka, ezinokwethenjelwa, nezisebenzayo. Usize ukwethula nokukala insiza ye-Amazon SageMaker enikwe amandla yi-AI/ML futhi usebenzise ubufakazi obuningi bomqondo esebenzisa izinsiza ze-Amazon AI. Uphinde wasungula inkundla yezibalo ezithuthukisiwe njengengxenye yohambo loguquko lwedijithali.

Kiran Challapalli ungunjiniyela webhizinisi ojulile onomkhakha womphakathi we-AWS. Uneminyaka engaphezu kwengu-8 yesipiliyoni ku-AI/ML kanye neminyaka engu-23 yokuthuthukiswa kwesofthiwe iyonke kanye nesipiliyoni sokuthengisa. I-Kiran isiza amabhizinisi omkhakha womphakathi kulo lonke elase-India ukuthi ahlole futhi adale ngokuhlanganyela izixazululo ezisekelwe emafini ezisebenzisa i-AI, ML, ne-AI ekhiqizayo—okuhlanganisa namamodeli ezilimi amakhulu—ubuchwepheshe.