def run_testing(
model: BaseModel,
test_dataset: ASRSliceDataset,
test_data_loader: tf.data.Dataset,
output: str,
):
with file_util.save_file(file_util.preprocess_paths(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 = model.predict(test_data_loader, verbose=1)
logger.info(f"Saving result to {output} ...")
with open(filepath, "w") as openfile:
openfile.write("PATH\tDURATION\tGROUNDTRUTH\tGREEDY\tBEAMSEARCH\n")
progbar = tqdm(total=test_dataset.total_steps, unit="batch")
for i, pred in enumerate(results):
groundtruth, greedy, beamsearch = [x.decode("utf-8") for x in pred]
path, duration, _ = test_dataset.entries[i]
openfile.write(f"{path}\t{duration}\t{groundtruth}\t{greedy}\t{beamsearch}\n")
progbar.update(1)
progbar.close()
app_util.evaluate_results(filepath)
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")
progbar = tqdm(total=test_dataset.total_steps, unit="batch")
for i, pred in enumerate(results):
groundtruth, greedy, beamsearch = [
x.decode('utf-8') for x in pred
]
path, duration, _ = test_dataset.entries[i]
openfile.write(
f"{path}\t{duration}\t{groundtruth}\t{greedy}\t{beamsearch}\n"
)
progbar.update(1)
progbar.close()
app_util.evaluate_results(filepath)