torch.manual_seed(config.seed); np.random.seed(config.seed)
# Initialize model
model = LanguageModel(config=config) #CTCModel(config=config)
print(model)
# Generate datasets
train_dataset, valid_dataset, test_dataset = get_text_datasets(config)
trainer = Trainer(model=model, config=config)
if restart: trainer.load_checkpoint()
# Train the final model
if train:
for epoch in range(config.num_epochs):
print("========= Epoch %d of %d =========" % (epoch+1, config.num_epochs))
train_loss = trainer.train(train_dataset)
model = model.cpu()
valid_loss = trainer.test(valid_dataset, set="valid")
if torch.cuda.is_available(): model = model.cuda()
print("========= Results: epoch %d of %d =========" % (epoch+1, config.num_epochs))
print("train loss: %.2f| valid loss: %.2f\n" % (train_loss, valid_loss) )
trainer.save_checkpoint()
trainer.load_best_model()
test_loss = trainer.test(test_dataset, set="test")
print("========= Test results =========")
print("test loss: %.2f \n" % (test_WER, test_loss) )
trainer = Trainer(model=model, config=config)
if train:
print("Training the controller...")
trainer.train_controller(train_dataset)
print("Done.")
for epoch in range(config.num_epochs):
print("========= Epoch %d of %d =========" %
(epoch + 1, config.num_epochs))
train_WER, train_loss, train_FLOPs_mean, train_FLOPs_std = trainer.train(
train_dataset)
if epoch % config.validation_period == 0:
model.sample_based_on_surprisal_during_testing = False
valid_WER_random, valid_loss_random, valid_FLOPs_mean_random, valid_FLOPs_std_random = trainer.test(
valid_dataset, set="valid")
trainer.save_checkpoint(WER=valid_WER_random,
sampling_method="random")
model.sample_based_on_surprisal_during_testing = True
valid_WER_surprisal, valid_loss_surprisal, valid_FLOPs_mean_surprisal, valid_FLOPs_std_surprisal = trainer.test(
valid_dataset, set="valid")
trainer.save_checkpoint(WER=valid_WER_surprisal,
sampling_method="surprisal")
print("========= Results: epoch %d of %d =========" %
(epoch + 1, config.num_epochs))
print("train WER: %.2f| train loss: %.2f| train FLOPs: %d" %
(train_WER * 100, train_loss, train_FLOPs_mean))
print(
"valid WER: %.2f| valid loss: %.2f| valid FLOPs: %d (random sampling)"
% (valid_WER_random * 100, valid_loss_random,
valid_FLOPs_mean_random))
print(
for epoch in range(config.num_epochs):
print("========= Epoch %d of %d =========" %
(epoch + 1, config.num_epochs))
train_WER, train_loss = trainer.train(train_dataset)
if epoch % config.validation_period == 0:
model = model.cpu()
valid_WER, valid_loss = trainer.test(valid_dataset, set="valid")
if torch.cuda.is_available(): model = model.cuda()
print("========= Results: epoch %d of %d =========" %
(epoch + 1, config.num_epochs))
print(
"train WER: %.2f| train loss: %.2f| valid WER: %.2f| valid loss: %.2f\n"
% (train_WER, train_loss, valid_WER, valid_loss))
trainer.save_checkpoint(WER=valid_WER)
trainer.load_best_model()
test_WER, test_loss = trainer.test(test_dataset, set="test")
print("========= Test results =========")
print("test WER: %.2f| test loss: %.2f \n" % (test_WER, test_loss))
def G2P(word):
x = train_dataset.word_tokenizer.EncodeAsIds(word)
T = [len(x)]
x = torch.tensor(x).unsqueeze(0).long()
y = model.infer(x, T)
phonemes = train_dataset.phoneme_tokenizer.DecodeIds(y[0])
return phonemes
import torch
from models import HMM
from data import get_datasets, read_config
from training import Trainer
# Generate datasets from text file
path = "data"
N = 128
config = read_config(N,path)
train_dataset, valid_dataset = get_datasets(config)
checkpoint_path = "."
# Initialize model
model = HMM(config=config)
# Train the model
num_epochs = 10
trainer = Trainer(model, config, lr=0.003)
trainer.load_checkpoint(checkpoint_path)
for epoch in range(num_epochs):
print("========= Epoch %d of %d =========" % (epoch+1, num_epochs))
train_loss = trainer.train(train_dataset)
valid_loss = trainer.test(valid_dataset)
trainer.save_checkpoint(epoch, checkpoint_path)
print("========= Results: epoch %d of %d =========" % (epoch+1, num_epochs))
print("train loss: %.2f| valid loss: %.2f\n" % (train_loss, valid_loss) )
