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, ) jasper = Jasper(**config.model_config, vocabulary_size=text_featurizer.num_classes) jasper.make(speech_featurizer.shape) jasper.load_weights(saved, by_name=True) jasper.summary(line_length=100) jasper.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=jasper, test_dataset=test_dataset, test_data_loader=test_data_loader, output=output)
def test_jasper(): config = Config(DEFAULT_YAML) text_featurizer = CharFeaturizer(config.decoder_config) speech_featurizer = TFSpeechFeaturizer(config.speech_config) model = Jasper(vocabulary_size=text_featurizer.num_classes, **config.model_config) model.make(speech_featurizer.shape) model.summary(line_length=150) model.add_featurizers(speech_featurizer=speech_featurizer, text_featurizer=text_featurizer) concrete_func = model.make_tflite_function( greedy=False).get_concrete_function() converter = tf.lite.TFLiteConverter.from_concrete_functions( [concrete_func]) converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.experimental_new_converter = True converter.target_spec.supported_ops = [ tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS ] converter.convert() print("Converted successfully with beam search") concrete_func = model.make_tflite_function( greedy=True).get_concrete_function() converter = tf.lite.TFLiteConverter.from_concrete_functions( [concrete_func]) converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.experimental_new_converter = True converter.target_spec.supported_ops = [ tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS ] converter.convert() print("Converted successfully with greedy")
speech_featurizer=speech_featurizer, text_featurizer=text_featurizer, **vars(config.learning_config.test_dataset_config)) else: test_dataset = ASRSliceDataset( speech_featurizer=speech_featurizer, text_featurizer=text_featurizer, **vars(config.learning_config.test_dataset_config)) # build model jasper = Jasper(**config.model_config, vocabulary_size=text_featurizer.num_classes) jasper.make(speech_featurizer.shape) jasper.load_weights(args.saved) jasper.summary(line_length=100) jasper.add_featurizers(speech_featurizer, text_featurizer) batch_size = args.bs or config.learning_config.running_config.batch_size test_data_loader = test_dataset.create(batch_size) with file_util.save_file(file_util.preprocess_paths(args.output)) as filepath: overwrite = True if tf.io.gfile.exists(filepath): overwrite = input( f"Overwrite existing result file {filepath} ? (y/n): ").lower( ) == "y" if overwrite: results = jasper.predict(test_data_loader, verbose=1) print(f"Saving result to {args.output} ...") with open(filepath, "w") as openfile: openfile.write("PATH\tDURATION\tGROUNDTRUTH\tGREEDY\tBEAMSEARCH\n")