mirror of
https://github.com/coqui-ai/TTS.git
synced 2025-12-24 20:29:30 +01:00
6fdb88f8e2
* add configs * Update config file * Add model configs * Add model layers * Add layer files * Add layer modules * change config names * Add emotion manager * fIX missing ap bug * Fix missing ap bug * Add base TTS e2e class * Fix wrong variable name in load_tts_samples * Add training script * Remove range predictor and gaussian upsampling * Add helper function * Add vctk recipe * Add conformer docs * Fix linting in conformer.py * Add Docs * remove duplicate import * refactor args * Fix bugs * Removew emotion embedding * remove unused arg * Remove emotion embedding arg * Remove emotion embedding arg * fix style issues * Fix bugs * Fix bugs * Add unittests * make style * fix formatter bug * fix test * Add pyworld compute pitch func * Update requirments.txt * Fix dataset Bug * Chnge layer norm to instance norm * Add missing import * Remove emotions.py * remove ssim loss * Add init layers func to aligner * refactor model layers * remove audio_config arg * Rename loss func * Rename to delightful-tts * Rename loss func * Remove unused modules * refactor imports * replace audio config with audio processor * Add change sample rate option * remove broken resample func * update recipe * fix style, add config docs * fix tests and multispeaker embd dim * remove pyworld * Make style and fix inference * Split tts tests * Fixup * Fixup * Fixup * Add argument names * Set "random" speaker in the model Tortoise/Bark * Use a diff f0_cache path for delightfull tts * Fix delightful speaker handling * Fix lint * Make style --------- Co-authored-by: loganhart420 <loganartpersonal@gmail.com> Co-authored-by: Eren Gölge <erogol@hotmail.com>
108 lines
3.5 KiB
Python
108 lines
3.5 KiB
Python
import torch
|
|
|
|
from TTS.tts.layers.feed_forward.decoder import Decoder
|
|
from TTS.tts.layers.feed_forward.encoder import Encoder
|
|
from TTS.tts.utils.helpers import sequence_mask
|
|
|
|
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
|
|
|
|
|
|
def test_encoder():
|
|
input_dummy = torch.rand(8, 14, 37).to(device)
|
|
input_lengths = torch.randint(31, 37, (8,)).long().to(device)
|
|
input_lengths[-1] = 37
|
|
input_mask = torch.unsqueeze(sequence_mask(input_lengths, input_dummy.size(2)), 1).to(device)
|
|
# relative positional transformer encoder
|
|
layer = Encoder(
|
|
out_channels=11,
|
|
in_hidden_channels=14,
|
|
encoder_type="relative_position_transformer",
|
|
encoder_params={
|
|
"hidden_channels_ffn": 768,
|
|
"num_heads": 2,
|
|
"kernel_size": 3,
|
|
"dropout_p": 0.1,
|
|
"num_layers": 6,
|
|
"rel_attn_window_size": 4,
|
|
"input_length": None,
|
|
},
|
|
).to(device)
|
|
output = layer(input_dummy, input_mask)
|
|
assert list(output.shape) == [8, 11, 37]
|
|
# residual conv bn encoder
|
|
layer = Encoder(
|
|
out_channels=11,
|
|
in_hidden_channels=14,
|
|
encoder_type="residual_conv_bn",
|
|
encoder_params={"kernel_size": 4, "dilations": 4 * [1, 2, 4] + [1], "num_conv_blocks": 2, "num_res_blocks": 13},
|
|
).to(device)
|
|
output = layer(input_dummy, input_mask)
|
|
assert list(output.shape) == [8, 11, 37]
|
|
# FFTransformer encoder
|
|
layer = Encoder(
|
|
out_channels=14,
|
|
in_hidden_channels=14,
|
|
encoder_type="fftransformer",
|
|
encoder_params={"hidden_channels_ffn": 31, "num_heads": 2, "num_layers": 2, "dropout_p": 0.1},
|
|
).to(device)
|
|
output = layer(input_dummy, input_mask)
|
|
assert list(output.shape) == [8, 14, 37]
|
|
|
|
|
|
def test_decoder():
|
|
input_dummy = torch.rand(8, 128, 37).to(device)
|
|
input_lengths = torch.randint(31, 37, (8,)).long().to(device)
|
|
input_lengths[-1] = 37
|
|
|
|
input_mask = torch.unsqueeze(sequence_mask(input_lengths, input_dummy.size(2)), 1).to(device)
|
|
# residual bn conv decoder
|
|
layer = Decoder(out_channels=11, in_hidden_channels=128).to(device)
|
|
output = layer(input_dummy, input_mask)
|
|
assert list(output.shape) == [8, 11, 37]
|
|
# transformer decoder
|
|
layer = Decoder(
|
|
out_channels=11,
|
|
in_hidden_channels=128,
|
|
decoder_type="relative_position_transformer",
|
|
decoder_params={
|
|
"hidden_channels_ffn": 128,
|
|
"num_heads": 2,
|
|
"kernel_size": 3,
|
|
"dropout_p": 0.1,
|
|
"num_layers": 8,
|
|
"rel_attn_window_size": 4,
|
|
"input_length": None,
|
|
},
|
|
).to(device)
|
|
output = layer(input_dummy, input_mask)
|
|
assert list(output.shape) == [8, 11, 37]
|
|
# wavenet decoder
|
|
layer = Decoder(
|
|
out_channels=11,
|
|
in_hidden_channels=128,
|
|
decoder_type="wavenet",
|
|
decoder_params={
|
|
"num_blocks": 12,
|
|
"hidden_channels": 192,
|
|
"kernel_size": 5,
|
|
"dilation_rate": 1,
|
|
"num_layers": 4,
|
|
"dropout_p": 0.05,
|
|
},
|
|
).to(device)
|
|
output = layer(input_dummy, input_mask)
|
|
# FFTransformer decoder
|
|
layer = Decoder(
|
|
out_channels=11,
|
|
in_hidden_channels=128,
|
|
decoder_type="fftransformer",
|
|
decoder_params={
|
|
"hidden_channels_ffn": 31,
|
|
"num_heads": 2,
|
|
"dropout_p": 0.1,
|
|
"num_layers": 2,
|
|
},
|
|
).to(device)
|
|
output = layer(input_dummy, input_mask)
|
|
assert list(output.shape) == [8, 11, 37]
|