Step 1

PeechApp · Feb 8, 2024 · afb63b7 · afb63b7
1 parent 577a481
commit afb63b7
Show file tree

Hide file tree

Showing 220 changed files with 253 additions and 253 deletions.
diff --git a/advanced-demo.ipynb b/advanced-demo.ipynb
@@ -27,7 +27,7 @@
     "from sklearn.preprocessing import StandardScaler\n",
     "import torch\n",
     "\n",
-    "from model.helpers.tools import get_mask_from_lengths\n",
+    "from models.helpers.tools import get_mask_from_lengths\n",
     "from training.datasets import LibriTTSDatasetAcoustic\n",
     "from training.loss import FastSpeech2LossGen, Metrics\n",
     "from training.modules import AcousticModule\n",

diff --git a/docs/index.md b/docs/index.md
@@ -17,28 +17,28 @@ Description of the training process. Docs, ideas and examples for the training p
 
 ## Model
 
-### [Acoustic Model](model/acoustic_model/readme.md)
+### [Acoustic Model](models/acoustic_model/readme.md)
 
 The [DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021](https://arxiv.org/abs/2110.12612) AcousticModel class represents a PyTorch module for an acoustic model in text-to-speech (TTS).
 The acoustic model is responsible for predicting speech signals from phoneme sequences.
 
 The model comprises multiple sub-modules including encoder, decoder and various prosody encoders and predictors.
 Additionally, a pitch and length adaptor are instantiated.
 
-### [Reference Encoder](model/reference_encoder/readme.md)
+### [Reference Encoder](models/reference_encoder/readme.md)
 
 Similar to Tacotron model, the reference encoder is used to extract the high-level features from the reference
 
-### [Convolution Blocks](model/conv_blocks/readme.md)
+### [Convolution Blocks](models/conv_blocks/readme.md)
 
 This part of the code responsible for the convolution blocks used in the model. Based on the FastSpeech models from [FastSpeech: Fast, Robust and Controllable Text to Speech](https://arxiv.org/abs/1905.09263) by Yi Ren et al and [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://arxiv.org/abs/2006.04558) by Yi Ren et al.
 
-### [Attention](model/attention/readme.md)
+### [Attention](models/attention/readme.md)
 
 Attention mechanizm used in the model. The concept of "global style tokens" (GST) was introduced in 
 [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://arxiv.org/abs/1803.09017) by Yuxuan Wang et al.
 
-### [Univnet](model/univnet/readme.md)
+### [Univnet](models/univnet/readme.md)
 
 [UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation](https://arxiv.org/abs/2106.07889v1)
 

diff --git a/docs/model/acoustic_model/acoustic_model.md b/docs/model/acoustic_model/acoustic_model.md
diff --git a/docs/model/acoustic_model/aligner.md b/docs/model/acoustic_model/aligner.md
diff --git a/docs/model/acoustic_model/embedding.md b/docs/model/acoustic_model/embedding.md
diff --git a/docs/model/acoustic_model/helpers.md b/docs/model/acoustic_model/helpers.md
diff --git a/docs/model/acoustic_model/length_adaptor.md b/docs/model/acoustic_model/length_adaptor.md
diff --git a/docs/model/acoustic_model/mas.md b/docs/model/acoustic_model/mas.md
diff --git a/docs/model/acoustic_model/phoneme_prosody_predictor.md b/docs/model/acoustic_model/phoneme_prosody_predictor.md
diff --git a/docs/model/acoustic_model/pitch_adaptor.md b/docs/model/acoustic_model/pitch_adaptor.md
diff --git a/docs/model/acoustic_model/pitch_adaptor2.md b/docs/model/acoustic_model/pitch_adaptor2.md
diff --git a/docs/model/acoustic_model/variance_predictor.md b/docs/model/acoustic_model/variance_predictor.md
diff --git a/docs/model/attention/conformer.md b/docs/model/attention/conformer.md
diff --git a/docs/model/attention/conformer_block.md b/docs/model/attention/conformer_block.md
diff --git a/docs/model/attention/conformer_conv_module.md b/docs/model/attention/conformer_conv_module.md
diff --git a/docs/model/attention/conformer_multi_headed_self_attention.md b/docs/model/attention/conformer_multi_headed_self_attention.md
diff --git a/docs/model/attention/feed_forward.md b/docs/model/attention/feed_forward.md
diff --git a/docs/model/attention/multi_head_attention.md b/docs/model/attention/multi_head_attention.md
diff --git a/docs/model/attention/relative_multi_head_attention.md b/docs/model/attention/relative_multi_head_attention.md
diff --git a/docs/model/attention/style_embed_attention.md b/docs/model/attention/style_embed_attention.md
diff --git a/docs/model/config/langs.md b/docs/model/config/langs.md
diff --git a/docs/model/conv_blocks/activation.md b/docs/model/conv_blocks/activation.md
diff --git a/docs/model/conv_blocks/add_coords.md b/docs/model/conv_blocks/add_coords.md
diff --git a/docs/model/conv_blocks/bsconv.md b/docs/model/conv_blocks/bsconv.md
diff --git a/docs/model/conv_blocks/conv1d.md b/docs/model/conv_blocks/conv1d.md
diff --git a/docs/model/conv_blocks/conv1d_glu.md b/docs/model/conv_blocks/conv1d_glu.md
diff --git a/docs/model/conv_blocks/conv_transposed.md b/docs/model/conv_blocks/conv_transposed.md
diff --git a/docs/model/conv_blocks/coord_conv1d.md b/docs/model/conv_blocks/coord_conv1d.md
diff --git a/docs/model/helpers/initializer.md b/docs/model/helpers/initializer.md
diff --git a/docs/model/helpers/tools.md b/docs/model/helpers/tools.md
diff --git a/docs/model/reference_encoder/STL.md b/docs/model/reference_encoder/STL.md
diff --git a/docs/model/reference_encoder/phoneme_level_prosody_encoder.md b/docs/model/reference_encoder/phoneme_level_prosody_encoder.md
diff --git a/docs/model/reference_encoder/reference_encoder.md b/docs/model/reference_encoder/reference_encoder.md
diff --git a/docs/model/reference_encoder/utterance_level_prosody_encoder.md b/docs/model/reference_encoder/utterance_level_prosody_encoder.md
diff --git a/docs/model/univnet/discriminator.md b/docs/model/univnet/discriminator.md
diff --git a/docs/model/univnet/discriminator_p.md b/docs/model/univnet/discriminator_p.md
diff --git a/docs/model/univnet/discriminator_r.md b/docs/model/univnet/discriminator_r.md
diff --git a/docs/model/univnet/kernel_predictor.md b/docs/model/univnet/kernel_predictor.md
diff --git a/docs/model/univnet/lvc_block.md b/docs/model/univnet/lvc_block.md
diff --git a/docs/model/univnet/multi_period_discriminator.md b/docs/model/univnet/multi_period_discriminator.md
diff --git a/docs/model/univnet/multi_resolution_discriminator.md b/docs/model/univnet/multi_resolution_discriminator.md
diff --git a/docs/model/univnet/traced_univnet.md b/docs/model/univnet/traced_univnet.md
diff --git a/docs/model/univnet/univnet.md b/docs/model/univnet/univnet.md
diff --git a/docs/models/acoustic_model/acoustic_model.md b/docs/models/acoustic_model/acoustic_model.md
@@ -0,0 +1 @@
+::: models.acoustic_model.acoustic_model
diff --git a/docs/models/acoustic_model/aligner.md b/docs/models/acoustic_model/aligner.md
@@ -0,0 +1 @@
+::: models.acoustic_model.aligner
diff --git a/docs/models/acoustic_model/embedding.md b/docs/models/acoustic_model/embedding.md
@@ -0,0 +1 @@
+::: models.acoustic_model.embedding
diff --git a/docs/models/acoustic_model/helpers.md b/docs/models/acoustic_model/helpers.md
@@ -0,0 +1 @@
+::: models.acoustic_model.helpers
diff --git a/docs/models/acoustic_model/length_adaptor.md b/docs/models/acoustic_model/length_adaptor.md
@@ -0,0 +1 @@
+::: models.acoustic_model.length_adaptor
diff --git a/docs/models/acoustic_model/mas.md b/docs/models/acoustic_model/mas.md
@@ -0,0 +1 @@
+::: models.acoustic_model.mas
diff --git a/docs/models/acoustic_model/phoneme_prosody_predictor.md b/docs/models/acoustic_model/phoneme_prosody_predictor.md
@@ -0,0 +1 @@
+::: models.acoustic_model.phoneme_prosody_predictor
diff --git a/docs/models/acoustic_model/pitch_adaptor.md b/docs/models/acoustic_model/pitch_adaptor.md
@@ -0,0 +1 @@
+::: models.acoustic_model.pitch_adaptor
diff --git a/docs/models/acoustic_model/pitch_adaptor2.md b/docs/models/acoustic_model/pitch_adaptor2.md
@@ -0,0 +1 @@
+::: models.acoustic_model.pitch_adaptor2
diff --git a/docs/model/acoustic_model/readme.md → docs/models/acoustic_model/readme.md b/docs/model/acoustic_model/readme.md → docs/models/acoustic_model/readme.md
diff --git a/docs/models/acoustic_model/variance_predictor.md b/docs/models/acoustic_model/variance_predictor.md
@@ -0,0 +1 @@
+::: models.acoustic_model.variance_predictor
diff --git a/docs/models/attention/conformer.md b/docs/models/attention/conformer.md
@@ -0,0 +1 @@
+::: models.attention.conformer
diff --git a/docs/models/attention/conformer_block.md b/docs/models/attention/conformer_block.md
@@ -0,0 +1 @@
+::: models.attention.conformer_block
diff --git a/docs/models/attention/conformer_conv_module.md b/docs/models/attention/conformer_conv_module.md
@@ -0,0 +1 @@
+::: models.attention.conformer_conv_module
diff --git a/docs/models/attention/conformer_multi_headed_self_attention.md b/docs/models/attention/conformer_multi_headed_self_attention.md
@@ -0,0 +1 @@
+::: models.attention.conformer_multi_headed_self_attention
diff --git a/docs/models/attention/feed_forward.md b/docs/models/attention/feed_forward.md
@@ -0,0 +1 @@
+::: models.attention.feed_forward
diff --git a/docs/models/attention/multi_head_attention.md b/docs/models/attention/multi_head_attention.md
@@ -0,0 +1 @@
+::: models.attention.multi_head_attention
diff --git a/docs/model/attention/readme.md → docs/models/attention/readme.md b/docs/model/attention/readme.md → docs/models/attention/readme.md
diff --git a/docs/models/attention/relative_multi_head_attention.md b/docs/models/attention/relative_multi_head_attention.md
@@ -0,0 +1 @@
+::: models.attention.relative_multi_head_attention
diff --git a/docs/models/attention/style_embed_attention.md b/docs/models/attention/style_embed_attention.md
@@ -0,0 +1 @@
+::: models.attention.style_embed_attention
diff --git a/docs/models/config/langs.md b/docs/models/config/langs.md
@@ -0,0 +1 @@
+::: models.config.langs
diff --git a/docs/model/config/readme.md → docs/models/config/readme.md b/docs/model/config/readme.md → docs/models/config/readme.md
diff --git a/docs/models/conv_blocks/activation.md b/docs/models/conv_blocks/activation.md
@@ -0,0 +1 @@
+::: models.conv_blocks.activation
diff --git a/docs/models/conv_blocks/add_coords.md b/docs/models/conv_blocks/add_coords.md
@@ -0,0 +1 @@
+::: models.conv_blocks.add_coords
diff --git a/docs/models/conv_blocks/bsconv.md b/docs/models/conv_blocks/bsconv.md
@@ -0,0 +1 @@
+::: models.conv_blocks.bsconv
diff --git a/docs/models/conv_blocks/conv1d.md b/docs/models/conv_blocks/conv1d.md
@@ -0,0 +1 @@
+::: models.conv_blocks.conv1d
diff --git a/docs/models/conv_blocks/conv1d_glu.md b/docs/models/conv_blocks/conv1d_glu.md
@@ -0,0 +1 @@
+::: models.conv_blocks.conv1d_glu
diff --git a/docs/models/conv_blocks/conv_transposed.md b/docs/models/conv_blocks/conv_transposed.md
@@ -0,0 +1 @@
+::: models.conv_blocks.conv_transposed
diff --git a/docs/models/conv_blocks/coord_conv1d.md b/docs/models/conv_blocks/coord_conv1d.md
@@ -0,0 +1 @@
+::: models.conv_blocks.coord_conv1d
diff --git a/docs/model/conv_blocks/readme.md → docs/models/conv_blocks/readme.md b/docs/model/conv_blocks/readme.md → docs/models/conv_blocks/readme.md
diff --git a/docs/models/helpers/initializer.md b/docs/models/helpers/initializer.md
@@ -0,0 +1 @@
+::: models.helpers.initializer
diff --git a/docs/model/helpers/readme.md → docs/models/helpers/readme.md b/docs/model/helpers/readme.md → docs/models/helpers/readme.md
diff --git a/docs/models/helpers/tools.md b/docs/models/helpers/tools.md
@@ -0,0 +1 @@
+::: models.helpers.tools
diff --git a/docs/models/reference_encoder/STL.md b/docs/models/reference_encoder/STL.md
@@ -0,0 +1 @@
+::: models.reference_encoder.STL
diff --git a/docs/models/reference_encoder/phoneme_level_prosody_encoder.md b/docs/models/reference_encoder/phoneme_level_prosody_encoder.md
@@ -0,0 +1 @@
+::: models.reference_encoder.phoneme_level_prosody_encoder
diff --git a/docs/model/reference_encoder/readme.md → docs/models/reference_encoder/readme.md b/docs/model/reference_encoder/readme.md → docs/models/reference_encoder/readme.md
diff --git a/docs/models/reference_encoder/reference_encoder.md b/docs/models/reference_encoder/reference_encoder.md
@@ -0,0 +1 @@
+::: models.reference_encoder.reference_encoder
diff --git a/docs/models/reference_encoder/utterance_level_prosody_encoder.md b/docs/models/reference_encoder/utterance_level_prosody_encoder.md
@@ -0,0 +1 @@
+::: models.reference_encoder.utterance_level_prosody_encoder
diff --git a/docs/models/univnet/discriminator.md b/docs/models/univnet/discriminator.md
@@ -0,0 +1 @@
+::: models.univnet.discriminator
diff --git a/docs/models/univnet/discriminator_p.md b/docs/models/univnet/discriminator_p.md
@@ -0,0 +1 @@
+::: models.univnet.discriminator_p
diff --git a/docs/models/univnet/discriminator_r.md b/docs/models/univnet/discriminator_r.md
@@ -0,0 +1 @@
+::: models.univnet.discriminator_r
diff --git a/docs/models/univnet/kernel_predictor.md b/docs/models/univnet/kernel_predictor.md
@@ -0,0 +1 @@
+::: models.univnet.kernel_predictor
diff --git a/docs/models/univnet/lvc_block.md b/docs/models/univnet/lvc_block.md
@@ -0,0 +1 @@
+::: models.univnet.lvc_block
diff --git a/docs/models/univnet/multi_period_discriminator.md b/docs/models/univnet/multi_period_discriminator.md
@@ -0,0 +1 @@
+::: models.univnet.multi_period_discriminator
diff --git a/docs/models/univnet/multi_resolution_discriminator.md b/docs/models/univnet/multi_resolution_discriminator.md
@@ -0,0 +1 @@
+::: models.univnet.multi_resolution_discriminator
diff --git a/docs/model/univnet/readme.md → docs/models/univnet/readme.md b/docs/model/univnet/readme.md → docs/models/univnet/readme.md
diff --git a/docs/models/univnet/traced_univnet.md b/docs/models/univnet/traced_univnet.md
@@ -0,0 +1 @@
+::: models.univnet.traced_univnet
diff --git a/docs/models/univnet/univnet.md b/docs/models/univnet/univnet.md
@@ -0,0 +1 @@
+::: models.univnet.univnet
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		::: models.acoustic_model.phoneme_prosody_predictor
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		::: models.attention.conformer_multi_headed_self_attention
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		::: models.attention.relative_multi_head_attention
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		::: models.reference_encoder.phoneme_level_prosody_encoder
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		::: models.reference_encoder.utterance_level_prosody_encoder
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		::: models.univnet.multi_resolution_discriminator