Spaces:
Runtime error
Runtime error
File size: 4,749 Bytes
24829a1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
import ast
import pprint
class HParams(object):
def __init__(self, **kwargs): self.__dict__.update(kwargs)
def __setitem__(self, key, value): setattr(self, key, value)
def __getitem__(self, key): return getattr(self, key)
def __repr__(self): return pprint.pformat(self.__dict__)
def parse(self, string):
# Overrides hparams from a comma-separated string of name=value pairs
if len(string) > 0:
overrides = [s.split("=") for s in string.split(",")]
keys, values = zip(*overrides)
keys = list(map(str.strip, keys))
values = list(map(str.strip, values))
for k in keys:
self.__dict__[k] = ast.literal_eval(values[keys.index(k)])
return self
hparams = HParams(
### Signal Processing (used in both synthesizer and vocoder)
sample_rate = 16000,
n_fft = 800,
num_mels = 80,
hop_size = 200, # Tacotron uses 12.5 ms frame shift (set to sample_rate * 0.0125)
win_size = 800, # Tacotron uses 50 ms frame length (set to sample_rate * 0.050)
fmin = 55,
min_level_db = -100,
ref_level_db = 20,
max_abs_value = 4., # Gradient explodes if too big, premature convergence if too small.
preemphasis = 0.97, # Filter coefficient to use if preemphasize is True
preemphasize = True,
### Tacotron Text-to-Speech (TTS)
tts_embed_dims = 512, # Embedding dimension for the graphemes/phoneme inputs
tts_encoder_dims = 256,
tts_decoder_dims = 128,
tts_postnet_dims = 512,
tts_encoder_K = 5,
tts_lstm_dims = 1024,
tts_postnet_K = 5,
tts_num_highways = 4,
tts_dropout = 0.5,
tts_cleaner_names = ["english_cleaners"],
tts_stop_threshold = -3.4, # Value below which audio generation ends.
# For example, for a range of [-4, 4], this
# will terminate the sequence at the first
# frame that has all values < -3.4
### Tacotron Training
tts_schedule = [(2, 1e-3, 20_000, 12), # Progressive training schedule
(2, 5e-4, 40_000, 12), # (r, lr, step, batch_size)
(2, 2e-4, 80_000, 12), #
(2, 1e-4, 160_000, 12), # r = reduction factor (# of mel frames
(2, 3e-5, 320_000, 12), # synthesized for each decoder iteration)
(2, 1e-5, 640_000, 12)], # lr = learning rate
tts_clip_grad_norm = 1.0, # clips the gradient norm to prevent explosion - set to None if not needed
tts_eval_interval = 500, # Number of steps between model evaluation (sample generation)
# Set to -1 to generate after completing epoch, or 0 to disable
tts_eval_num_samples = 1, # Makes this number of samples
### Data Preprocessing
max_mel_frames = 900,
rescale = True,
rescaling_max = 0.9,
synthesis_batch_size = 16, # For vocoder preprocessing and inference.
### Mel Visualization and Griffin-Lim
signal_normalization = True,
power = 1.5,
griffin_lim_iters = 60,
### Audio processing options
fmax = 7600, # Should not exceed (sample_rate // 2)
allow_clipping_in_normalization = True, # Used when signal_normalization = True
clip_mels_length = True, # If true, discards samples exceeding max_mel_frames
use_lws = False, # "Fast spectrogram phase recovery using local weighted sums"
symmetric_mels = True, # Sets mel range to [-max_abs_value, max_abs_value] if True,
# and [0, max_abs_value] if False
trim_silence = True, # Use with sample_rate of 16000 for best results
### SV2TTS
speaker_embedding_size = 256, # Dimension for the speaker embedding
silence_min_duration_split = 0.4, # Duration in seconds of a silence for an utterance to be split
utterance_min_duration = 1.6, # Duration in seconds below which utterances are discarded
)
def hparams_debug_string():
return str(hparams)
|