taco/microWakeWord-Trainer-Nvidia-Docker
1
0
Fork 0
mirror of https://github.com/TaterTotterson/microWakeWord-Trainer-Nvidia-Docker.git synced 2026-06-12 20:10:19 -06:00
Code Issues Packages Projects Releases Wiki Activity

Sat Samples

Browse Source
This commit is contained in:
MasterPhooey
2026-04-25 07:29:23 -05:00
parent 51cbf6fd90
commit 318a4ad3b5
7 changed files with 3946 additions and 302 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
cli/wake_word_sample_augmenter
View File

@@ -18,6 +18,8 @@ parser.add_argument("--output-dir", type=str, help="Wake word output dir. Defaul
# Personal inputs/outputs (NEW)
parser.add_argument("--personal-dir", type=str, help="Personal WAV dir. Default: <data-dir>/personal_samples", required=False)
parser.add_argument("--personal-output-dir", type=str, help="Personal features output dir. Default: <data-dir>/work/personal_augmented_features", required=False)
parser.add_argument("--negative-dir", type=str, help="Reviewed negative WAV dir. Default: <data-dir>/negative_samples", required=False)
parser.add_argument("--negative-output-dir", type=str, help="Reviewed negative features output dir. Default: <data-dir>/work/reviewed_negative_features", required=False)
# Dataset dirs
parser.add_argument("--mit-rirs-16k-dir", type=str, help="MIT RIR input directory. Default: <data-dir>/training_datasets/mit_rirs_16k", required=False)
@@ -57,6 +59,17 @@ if not args.personal_output_dir:
else:
args.personal_output_dir = os.path.realpath(args.personal_output_dir)
# Reviewed negative defaults
if not args.negative_dir:
args.negative_dir = os.path.join(args.data_dir, "negative_samples")
else:
args.negative_dir = os.path.realpath(args.negative_dir)
if not args.negative_output_dir:
args.negative_output_dir = os.path.join(work_dir, "reviewed_negative_features")
else:
args.negative_output_dir = os.path.realpath(args.negative_output_dir)
# Dataset defaults
if not args.mit_rirs_16k_dir:
args.mit_rirs_16k_dir = os.path.join(args.data_dir, "training_datasets", "mit_rirs_16k")
@@ -205,7 +218,7 @@ def bind_wav_generator(clips_obj: Clips, wav_dir: str):
clips_obj.audio_generator = types.MethodType(audio_generator_from_wavs, clips_obj)
def generate_feature_set(input_wav_dir: str, out_root_dir: str, label: str):
def generate_feature_set(input_wav_dir: str, out_root_dir: str, label: str, *, remove_silence: bool = True):
files = glob.glob(os.path.join(input_wav_dir, "*.wav"))
if not files:
print(f"ℹ️ No WAVs found for {label} in: {input_wav_dir} (skipping)")
@@ -218,7 +231,7 @@ def generate_feature_set(input_wav_dir: str, out_root_dir: str, label: str):
input_directory=input_wav_dir,
file_pattern="*.wav",
max_clip_duration_s=5,
remove_silence=True,
remove_silence=remove_silence,
random_split_seed=10,
split_count=0.1,
)
@@ -263,9 +276,12 @@ def generate_feature_set(input_wav_dir: str, out_root_dir: str, label: str):
# Wake word generated/TTS features (existing behavior)
generate_feature_set(args.input_dir, args.output_dir, "generated")
# Personal features (NEW)
# Personal features
generate_feature_set(args.personal_dir, args.personal_output_dir, "personal")
# Reviewed false-positive / hard-negative features
generate_feature_set(args.negative_dir, args.negative_output_dir, "reviewed negatives", remove_silence=False)
END_TIME = datetime.now(timezone.utc).replace(microsecond=0)
et = END_TIME - START_TIME
print(f"\n{'=' * 80}")