Skip to content

Add config option for other language #183

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add config option for other language #183

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions examples/custom_model.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,20 @@ piper_sample_generator_path: "./piper-sample-generator"
# Sub-directories will be automatically created for train and test clips for both positive and negative examples
output_dir: "./my_custom_model"

# The path to model used by piper_sample_generator
generator_model: "./piper-sample-generator/models/en_US-libritts_r-medium.pt"

# Min phoneme count for piper_sample_generator
min_phoneme_count: null

# Noise setting for trainning samples
noise_scales_train:
- 0.98

# Noise setting for testing samples
noise_scales_test:
- 1.0

# The directories containing Room Impulse Response recordings
rir_paths:
- "./mit_rirs"
Expand Down
20 changes: 16 additions & 4 deletions openwakeword/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -669,7 +669,9 @@ def convert_onnx_to_tflite(onnx_model_path, output_path):
generate_samples(
text=config["target_phrase"], max_samples=config["n_samples"]-n_current_samples,
batch_size=config["tts_batch_size"],
noise_scales=[0.98], noise_scale_ws=[0.98], length_scales=[0.75, 1.0, 1.25],
model = config["generator_model"],
min_phoneme_count=config["min_phoneme_count"],
noise_scales=config["noise_scales_train"], noise_scale_ws=config["noise_scales_train"], length_scales=[0.75, 1.0, 1.25],
output_dir=positive_train_output_dir, auto_reduce_batch_size=True,
file_names=[uuid.uuid4().hex + ".wav" for i in range(config["n_samples"])]
)
Expand All @@ -685,7 +687,9 @@ def convert_onnx_to_tflite(onnx_model_path, output_path):
if n_current_samples <= 0.95*config["n_samples_val"]:
generate_samples(text=config["target_phrase"], max_samples=config["n_samples_val"]-n_current_samples,
batch_size=config["tts_batch_size"],
noise_scales=[1.0], noise_scale_ws=[1.0], length_scales=[0.75, 1.0, 1.25],
model = config["generator_model"],
min_phoneme_count=config["min_phoneme_count"],
noise_scales=config["noise_scales_test"], noise_scale_ws=config["noise_scales_test"], length_scales=[0.75, 1.0, 1.25],
output_dir=positive_test_output_dir, auto_reduce_batch_size=True)
torch.cuda.empty_cache()
else:
Expand All @@ -706,7 +710,11 @@ def convert_onnx_to_tflite(onnx_model_path, output_path):
include_input_words=0.2))
generate_samples(text=adversarial_texts, max_samples=config["n_samples"]-n_current_samples,
batch_size=config["tts_batch_size"]//7,
noise_scales=[0.98], noise_scale_ws=[0.98], length_scales=[0.75, 1.0, 1.25],
model = config["generator_model"],
min_phoneme_count=config["min_phoneme_count"],
noise_scales=config["noise_scales_train"],
noise_scale_ws=config["noise_scales_train"],
length_scales=[0.75, 1.0, 1.25],
output_dir=negative_train_output_dir, auto_reduce_batch_size=True,
file_names=[uuid.uuid4().hex + ".wav" for i in range(config["n_samples"])]
)
Expand All @@ -729,7 +737,11 @@ def convert_onnx_to_tflite(onnx_model_path, output_path):
include_input_words=0.2))
generate_samples(text=adversarial_texts, max_samples=config["n_samples_val"]-n_current_samples,
batch_size=config["tts_batch_size"]//7,
noise_scales=[1.0], noise_scale_ws=[1.0], length_scales=[0.75, 1.0, 1.25],
model = config["generator_model"],
min_phoneme_count=config["min_phoneme_count"],
noise_scales=config["noise_scales_test"],
noise_scale_ws=config["noise_scales_test"],
length_scales=[0.75, 1.0, 1.25],
output_dir=negative_test_output_dir, auto_reduce_batch_size=True)
torch.cuda.empty_cache()
else:
Expand Down