Hi, So I converted Fastspeech2 model to TFlite, when I tried to inference from TFlite I am getting this error

decoder_output_tflite, mel_output_tflite = infer(input_text) interpreter.invoke() File “/home/zak/venv/lib/python3.8/site-packages/tensorflow/lite/python/interpreter.py”, line 539, in invoke self._interpreter.Invoke() RuntimeError: tensorflow/lite/kernels/reshape.cc:55 stretch_dim != -1 (0 != -1)Node number 83 (RESHAPE) failed to prepare.

the code I used for this purpose is

import numpy as np import yaml import tensorflow as tf

from tensorflow_tts.processor import ZAKSpeechProcessor from tensorflow_tts.processor.ZAKspeech import ZAKSPEECH_SYMBOLS

from tensorflow_tts.configs import FastSpeechConfig, FastSpeech2Config from tensorflow_tts.configs import MultiBandMelGANGeneratorConfig

from tensorflow_tts.models import TFFastSpeech, TFFastSpeech2 from tensorflow_tts.models import TFMBMelGANGenerator

from IPython.display import Audio

Load the TFLite model and allocate tensors.

interpreter = tf.lite.Interpreter(model_path=‘fastspeech2_quant.tflite’)

Get input and output tensors.

input_details = interpreter.get_input_details() output_details = interpreter.get_output_details()

Prepare input data.

def prepare_input(input_ids): input_ids = tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0) return (input_ids, tf.convert_to_tensor([0], tf.int32), tf.convert_to_tensor([1.0], dtype=tf.float32), tf.convert_to_tensor([1.0], dtype=tf.float32), tf.convert_to_tensor([1.0], dtype=tf.float32))

Test the model on random input data.

def infer(input_text): for x in input_details: print(x) for x in output_details: print(x) processor = ZAKSpeechProcessor(data_dir=None, symbols=ZAKSPEECH_SYMBOLS, cleaner_names=“arabic_cleaners”) input_ids = processor.text_to_sequence(input_text.lower()) interpreter.resize_tensor_input(input_details[0][‘index’], [1, len(input_ids)]) interpreter.resize_tensor_input(input_details[1][‘index’], [1]) interpreter.resize_tensor_input(input_details[2][‘index’], [1]) interpreter.resize_tensor_input(input_details[3][‘index’], [1]) interpreter.resize_tensor_input(input_details[4][‘index’], [1]) interpreter.allocate_tensors() input_data = prepare_input(input_ids) for i, detail in enumerate(input_details): input_shape = detail[‘shape’] interpreter.set_tensor(detail[‘index’], input_data[i])

interpreter.invoke()

The function get_tensor() returns a copy of the tensor data.

Use tensor() in order to get a pointer to the tensor.

return (interpreter.get_tensor(output_details[0][‘index’]), interpreter.get_tensor(output_details[1][‘index’]))

initialize melgan model

with open(‘…/examples/multiband_melgan/conf/multiband_melgan.v1.yaml’) as f: mb_melgan_config = yaml.load(f, Loader=yaml.Loader) mb_melgan_config = MultiBandMelGANGeneratorConfig(**mb_melgan_config[“multiband_melgan_generator_params”]) mb_melgan = TFMBMelGANGenerator(config=mb_melgan_config, name=‘mb_melgan_generator’) mb_melgan._build() mb_melgan.load_weights(“…/examples/multiband_melgan/exp/train.multiband_melgan.v1/checkpoints/generator-1000000.h5”)

input_text = “”

decoder_output_tflite, mel_output_tflite = infer(input_text) audio_before_tflite = mb_melgan(decoder_output_tflite)[0, :, 0] audio_after_tflite = mb_melgan(mel_output_tflite)[0, :, 0]

appreciate your help