def test_conformer():
config = Config(DEFAULT_YAML, learning=False)
text_featurizer = CharFeaturizer(config.decoder_config)
speech_featurizer = TFSpeechFeaturizer(config.speech_config)
model = Conformer(vocabulary_size=text_featurizer.num_classes, **config.model_config)
model._build(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(timestamp=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 no timestamp")
concrete_func = model.make_tflite_function(timestamp=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 timestamp")
#
# print(hyps[0])
#
# # hyps = model.recognize_beam(features)
#
#
# hyps = model.recognize_beam(tf.expand_dims(speech_featurizer.tf_extract(signal), 0))
# print(hyps)
# hyps = model.recognize_beam_tflite(signal)
# print(hyps.numpy().decode("utf-8"))
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]
tflite = converter.convert()
tflitemodel = tf.lite.Interpreter(model_content=tflite)
input_details = tflitemodel.get_input_details()
output_details = tflitemodel.get_output_details()
tflitemodel.resize_tensor_input(input_details[0]["index"], signal.shape)
tflitemodel.allocate_tensors()
tflitemodel.set_tensor(input_details[0]["index"], signal)
tflitemodel.set_tensor(
speech_featurizer = TFSpeechFeaturizer(config.speech_config)
if args.subwords and os.path.exists(args.subwords):
print("Loading subwords ...")
text_featurizer = SubwordFeaturizer.load_from_file(config.decoder_config,
args.subwords)
else:
raise ValueError("subwords must be set")
# build model
conformer = Conformer(**config.model_config,
vocabulary_size=text_featurizer.num_classes)
conformer._build(speech_featurizer.shape)
conformer.load_weights(args.saved)
conformer.summary(line_length=150)
conformer.add_featurizers(speech_featurizer, text_featurizer)
concrete_func = conformer.make_tflite_function(
greedy=True).get_concrete_function()
converter = tf.lite.TFLiteConverter.from_concrete_functions([concrete_func])
#converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_ops = [
tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS
]
tflite_model = converter.convert()
if not os.path.exists(os.path.dirname(args.output)):
os.makedirs(os.path.dirname(args.output))
with open(args.output, "wb") as tflite_out:
tflite_out.write(tflite_model)
help="TFLite file path to be exported")
args = parser.parse_args()
assert args.saved and args.output
config = Config(args.config)
speech_featurizer = TFSpeechFeaturizer(config.speech_config)
text_featurizer = CharFeaturizer(config.decoder_config)
# build model
conformer = Conformer(**config.model_config,
vocabulary_size=text_featurizer.num_classes)
conformer._build(speech_featurizer.shape)
conformer.load_weights(args.saved)
conformer.summary(line_length=150)
conformer.add_featurizers(speech_featurizer, text_featurizer)
concrete_func = conformer.make_tflite_function().get_concrete_function()
converter = tf.lite.TFLiteConverter.from_concrete_functions([concrete_func])
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_ops = [
tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS
]
tflite_model = converter.convert()
if not os.path.exists(os.path.dirname(args.output)):
os.makedirs(os.path.dirname(args.output))
with open(args.output, "wb") as tflite_out:
tflite_out.write(tflite_model)
def test_conformer():
config = Config(DEFAULT_YAML)
text_featurizer = CharFeaturizer(config.decoder_config)
speech_featurizer = TFSpeechFeaturizer(config.speech_config)
model = Conformer(vocabulary_size=text_featurizer.num_classes,
**config.model_config)
model._build(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(
timestamp=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
]
tflite = converter.convert()
print("Converted successfully with no timestamp")
concrete_func = model.make_tflite_function(
timestamp=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 timestamp")
tflitemodel = tf.lite.Interpreter(model_content=tflite)
signal = tf.random.normal([4000])
input_details = tflitemodel.get_input_details()
output_details = tflitemodel.get_output_details()
tflitemodel.resize_tensor_input(input_details[0]["index"], [4000])
tflitemodel.allocate_tensors()
tflitemodel.set_tensor(input_details[0]["index"], signal)
tflitemodel.set_tensor(input_details[1]["index"],
tf.constant(text_featurizer.blank, dtype=tf.int32))
tflitemodel.set_tensor(
input_details[2]["index"],
tf.zeros([
config.model_config["prediction_num_rnns"], 2, 1,
config.model_config["prediction_rnn_units"]
],
dtype=tf.float32))
tflitemodel.invoke()
hyp = tflitemodel.get_tensor(output_details[0]["index"])
print(hyp)
