serverless_asr.py

from sagemaker.huggingface.model import HuggingFaceModel
from sagemaker.serverless import ServerlessInferenceConfig
from sagemaker.serializers import DataSerializer
import sagemaker
import boto3

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

# Hub Model configuration. <https://huggingface.co/models>
hub = {
    'HF_MODEL_ID':'facebook/wav2vec2-base-960h',
    'HF_TASK':'automatic-speech-recognition',
}

# create Hugging Face Model Class
huggingface_model_sls = HuggingFaceModel(
   env=hub,                      # configuration for loading model from Hub
   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
)

# deploy the endpoint endpoint
predictor_sls = huggingface_model_sls.deploy(
    serverless_inference_config=ServerlessInferenceConfig(memory_size_in_mb=4096, max_concurrency=10),
    serializer=DataSerializer(content_type='audio/x-audio'), # serializer for our audio data.
)

# download sample audio file
# !wget https://cdn-media.huggingface.co/speech_samples/sample1.flac

# call inference with path to audio file
res = predictor_sls.predict(data="sample1.flac")
print(res)

# {'text': "GOING ALONG SLUSHY COUNTRY ROADS AND SPEAKING TO DAMP AUDIENCES IN DRAUGHTY SCHOOL ROOMS DAY AFTER DAY FOR A FORTNIGHT HE'LL HAVE TO PUT IN AN APPEARANCE AT SOME PLACE OF WORSHIP ON SUNDAY MORNING AND HE CAN COME TO US IMMEDIATELY AFTERWARDS"}