def main(
config: str = DEFAULT_YAML,
saved: str = None,
mxp: bool = False,
bs: int = None,
sentence_piece: bool = False,
subwords: bool = False,
device: int = 0,
cpu: bool = False,
output: str = "test.tsv",
):
assert saved and output
tf.random.set_seed(0)
tf.keras.backend.clear_session()
tf.config.optimizer.set_experimental_options({"auto_mixed_precision": mxp})
env_util.setup_devices([device], cpu=cpu)
config = Config(config)
speech_featurizer, text_featurizer = featurizer_helpers.prepare_featurizers(
config=config,
subwords=subwords,
sentence_piece=sentence_piece,
)
deepspeech2 = DeepSpeech2(**config.model_config,
vocabulary_size=text_featurizer.num_classes)
deepspeech2.make(speech_featurizer.shape)
deepspeech2.load_weights(saved, by_name=True)
deepspeech2.summary(line_length=100)
deepspeech2.add_featurizers(speech_featurizer, text_featurizer)
test_dataset = dataset_helpers.prepare_testing_datasets(
config=config,
speech_featurizer=speech_featurizer,
text_featurizer=text_featurizer)
batch_size = bs or config.learning_config.running_config.batch_size
test_data_loader = test_dataset.create(batch_size)
exec_helpers.run_testing(model=deepspeech2,
test_dataset=test_dataset,
test_data_loader=test_data_loader,
output=output)
action="store_true",
help="Whether to only use cpu")
parser.add_argument("--output",
type=str,
default="test.tsv",
help="Result filepath")
args = parser.parse_args()
assert args.saved
tf.config.optimizer.set_experimental_options(
{"auto_mixed_precision": args.mxp})
env_util.setup_devices([args.device], cpu=args.cpu)
from tensorflow_asr.configs.config import Config
from tensorflow_asr.datasets.asr_dataset import ASRTFRecordDataset, ASRSliceDataset
from tensorflow_asr.featurizers.speech_featurizers import TFSpeechFeaturizer
from tensorflow_asr.featurizers.text_featurizers import SubwordFeaturizer, SentencePieceFeaturizer, CharFeaturizer
from tensorflow_asr.models.ctc.jasper import Jasper
from tensorflow_asr.utils import app_util
config = Config(args.config)
speech_featurizer = TFSpeechFeaturizer(config.speech_config)
if args.sentence_piece:
print("Use SentencePiece ...")
text_featurizer = SentencePieceFeaturizer(config.decoder_config)
elif args.subwords:
