Update french model

README.md

@@ -0,0 +1,81 @@
+---
+tags:
+- tensorflowtts
+- audio
+- text-to-speech
+- mel-to-wav
+language: fr
+license: apache-2.0
+datasets:
+- synpaflex
+widget:
+- text: "Oh, je voudrais tant que tu te souviennes Des jours heureux quand nous étions amis"
+---
+
+# Multi-band MelGAN trained on Synpaflex (Fr)
+This repository provides a pretrained [Multi-band MelGAN](https://arxiv.org/abs/2005.05106) trained on Synpaflex dataset (French)). For a detail of the model, we encourage you to read more about
+[TensorFlowTTS](https://github.com/TensorSpeech/TensorFlowTTS). 
+
+
+## Install TensorFlowTTS
+First of all, please install TensorFlowTTS with the following command:
+```
+pip install TensorFlowTTS
+```
+
+### Converting your Text to Wav
+```python
+import soundfile as sf
+import numpy as np
+
+import tensorflow as tf
+
+from tensorflow_tts.inference import AutoProcessor
+from tensorflow_tts.inference import TFAutoModel
+
+processor = AutoProcessor.from_pretrained("tensorspeech/tts-tacotron2-synpaflex-fr")
+tacotron2 = TFAutoModel.from_pretrained("tensorspeech/tts-tacotron2-synpaflex-fr")
+mb_melgan = TFAutoModel.from_pretrained("tensorspeech/tts-mb_melgan-synpaflex-fr")
+
+text = "Oh, je voudrais tant que tu te souviennes Des jours heureux quand nous étions amis"
+
+input_ids = processor.text_to_sequence(text)
+
+# tacotron2 inference (text-to-mel)
+decoder_output, mel_outputs, stop_token_prediction, alignment_history = tacotron2.inference(
+    input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
+    input_lengths=tf.convert_to_tensor([len(input_ids)], tf.int32),
+    speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),
+)
+
+# melgan inference (mel-to-wav)
+audio = mb_melgan.inference(mel_outputs)[0, :, 0]
+
+# save to file
+sf.write('./audio.wav', audio, 22050, "PCM_16")
+```
+
+#### Referencing Multi-band MelGAN
+```
+@misc{yang2020multiband,
+      title={Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech}, 
+      author={Geng Yang and Shan Yang and Kai Liu and Peng Fang and Wei Chen and Lei Xie},
+      year={2020},
+      eprint={2005.05106},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD}
+}
+```
+
+#### Referencing TensorFlowTTS
+```
+@misc{TFTTS,
+    author = {Minh Nguyen, Alejandro Miguel Velasquez, Erogol, Kuan Chen, Dawid Kobus, Takuya Ebata, 
+    Trinh Le and Yunchao He},
+    title = {TensorflowTTS},
+    year = {2020},
+    publisher = {GitHub},
+    journal = {GitHub repository},
+    howpublished = {\\url{https://github.com/TensorSpeech/TensorFlowTTS}},
+  }
+```

config.yml

@@ -0,0 +1,107 @@
+# This is the hyperparameter configuration file for Multi-Band MelGAN.
+# Please make sure this is adjusted for the Synpaflex dataset. If you want to
+# apply to the other dataset, you might need to carefully change some parameters.
+# This configuration performs 1000k iters.
+
+###########################################################
+#                FEATURE EXTRACTION SETTING               #
+###########################################################
+sampling_rate: 22050
+hop_size: 256            # Hop size.
+format: "npy"
+
+
+###########################################################
+#         GENERATOR NETWORK ARCHITECTURE SETTING          #
+###########################################################
+model_type: "multiband_melgan_generator"
+
+multiband_melgan_generator_params:
+    out_channels: 4               # Number of output channels (number of subbands).
+    kernel_size: 7                # Kernel size of initial and final conv layers.
+    filters: 384                  # Initial number of channels for conv layers.
+    upsample_scales: [8, 4, 2]    # List of Upsampling scales.
+    stack_kernel_size: 3          # Kernel size of dilated conv layers in residual stack.
+    stacks: 4                     # Number of stacks in a single residual stack module.
+    is_weight_norm: false         # Use weight-norm or not.
+
+###########################################################
+#       DISCRIMINATOR NETWORK ARCHITECTURE SETTING        #
+###########################################################
+multiband_melgan_discriminator_params:
+    out_channels: 1                   # Number of output channels.
+    scales: 3                         # Number of multi-scales.
+    downsample_pooling: "AveragePooling1D"   # Pooling type for the input downsampling.
+    downsample_pooling_params:        # Parameters of the above pooling function.
+        pool_size: 4
+        strides: 2
+    kernel_sizes: [5, 3]              # List of kernel size.
+    filters: 16                       # Number of channels of the initial conv layer.
+    max_downsample_filters: 512       # Maximum number of channels of downsampling layers.
+    downsample_scales: [4, 4, 4]      # List of downsampling scales.
+    nonlinear_activation: "LeakyReLU" # Nonlinear activation function.
+    nonlinear_activation_params:      # Parameters of nonlinear activation function.
+        alpha: 0.2
+    is_weight_norm: false             # Use weight-norm or not.
+
+###########################################################
+#                   STFT LOSS SETTING                     #
+###########################################################
+stft_loss_params:
+    fft_lengths: [1024, 2048, 512]  # List of FFT size for STFT-based loss.
+    frame_steps: [120, 240, 50]     # List of hop size for STFT-based loss
+    frame_lengths: [600, 1200, 240] # List of window length for STFT-based loss.
+
+subband_stft_loss_params:
+    fft_lengths: [384, 683, 171]  # List of FFT size for STFT-based loss.
+    frame_steps: [30, 60, 10]     # List of hop size for STFT-based loss
+    frame_lengths: [150, 300, 60] # List of window length for STFT-based loss.
+
+###########################################################
+#               ADVERSARIAL LOSS SETTING                  #
+###########################################################
+lambda_feat_match: 10.0      # Loss balancing coefficient for feature matching loss
+lambda_adv: 2.5              # Loss balancing coefficient for adversarial loss.
+
+###########################################################
+#                  DATA LOADER SETTING                    #
+###########################################################
+batch_size: 64                 # Batch size for each GPU with assuming that gradient_accumulation_steps == 1.
+batch_max_steps: 8192          # Length of each audio in batch for training. Make sure dividable by hop_size.
+batch_max_steps_valid: 8192    # Length of each audio for validation. Make sure dividable by hope_size.
+remove_short_samples: true     # Whether to remove samples the length of which are less than batch_max_steps.
+allow_cache: true              # Whether to allow cache in dataset. If true, it requires cpu memory.
+is_shuffle: true               # shuffle dataset after each epoch.
+
+###########################################################
+#             OPTIMIZER & SCHEDULER SETTING               #
+###########################################################
+generator_optimizer_params:
+    lr_fn: "PiecewiseConstantDecay"
+    lr_params: 
+        boundaries: [100000, 200000, 300000, 400000, 500000, 600000, 700000]
+        values: [0.0005, 0.0005, 0.00025, 0.000125, 0.0000625, 0.00003125, 0.000015625, 0.000001]
+    amsgrad: false
+
+discriminator_optimizer_params:
+    lr_fn: "PiecewiseConstantDecay"
+    lr_params: 
+        boundaries: [100000, 200000, 300000, 400000, 500000]
+        values: [0.00025, 0.000125, 0.0000625, 0.00003125, 0.000015625, 0.000001]
+
+    amsgrad: false
+
+gradient_accumulation_steps: 1
+###########################################################
+#                    INTERVAL SETTING                     #
+###########################################################
+discriminator_train_start_steps: 200000  # steps begin training discriminator
+train_max_steps: 4000000                 # Number of training steps.
+save_interval_steps: 20000               # Interval steps to save checkpoint.
+eval_interval_steps: 5000                # Interval steps to evaluate the network.
+log_interval_steps: 200                  # Interval steps to record the training log.
+
+###########################################################
+#                     OTHER SETTING                       #
+###########################################################
+num_save_intermediate_results: 1  # Number of batch to be saved as intermediate results.

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9539a243656b2615d7c48997ea5bce8011684f86c14a30a6af19b9c149bf4de
+size 10232552