Skip to content
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

support for --phoneme-input for having pure phonemes as input #403

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+14 −2
Open

support for --phoneme-input for having pure phonemes as input #403

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
db28352
support for --phoneme-input for having pure phonemes as input instead…
Feb 17, 2024
aad321f
Merge branch 'rhasspy:master' into pure_phoneme_input
contentnation Jun 27, 2024
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
7 changes: 7 additions & 0 deletions src/python_run/piper/__main__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,12 @@ def main() -> None:
action="store_true",
help="Stream raw audio to stdout",
)
parser.add_argument(
"-p",
"--phoneme-input",
action="store_true",
help="Flag to use pure phonemes as input"
)
#
parser.add_argument("-s", "--speaker", type=int, help="Id of speaker (default: 0)")
parser.add_argument(
Expand Down Expand Up @@ -107,6 +113,7 @@ def main() -> None:
# Load voice
voice = PiperVoice.load(args.model, config_path=args.config, use_cuda=args.cuda)
synthesize_args = {
"phoneme_input": args.phoneme_input,
"speaker_id": args.speaker,
"length_scale": args.length_scale,
"noise_scale": args.noise_scale,
Expand Down
9 changes: 7 additions & 2 deletions src/python_run/piper/voice.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,6 +90,7 @@ def synthesize(
self,
text: str,
wav_file: wave.Wave_write,
phoneme_input: bool,
speaker_id: Optional[int] = None,
length_scale: Optional[float] = None,
noise_scale: Optional[float] = None,
Expand All @@ -103,6 +104,7 @@ def synthesize(

for audio_bytes in self.synthesize_stream_raw(
text,
phoneme_input=phoneme_input,
speaker_id=speaker_id,
length_scale=length_scale,
noise_scale=noise_scale,
Expand All @@ -114,15 +116,18 @@ def synthesize(
def synthesize_stream_raw(
self,
text: str,
phoneme_input: bool,
speaker_id: Optional[int] = None,
length_scale: Optional[float] = None,
noise_scale: Optional[float] = None,
noise_w: Optional[float] = None,
sentence_silence: float = 0.0,
) -> Iterable[bytes]:
"""Synthesize raw audio per sentence from text."""
sentence_phonemes = self.phonemize(text)

if phoneme_input:
sentence_phonemes = [list(text)]
else:
sentence_phonemes = self.phonemize(text)
# 16-bit mono
num_silence_samples = int(sentence_silence * self.config.sample_rate)
silence_bytes = bytes(num_silence_samples * 2)
Expand Down