rust/delayed-streams-modeling
1
0
Fork 0
mirror of https://github.com/kyutai-labs/delayed-streams-modeling.git synced 2026-01-07 09:42:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:kyutai-labs/delayed-streams-modeling into vv/rust-example

Browse Source
This commit is contained in:
Václav Volhejn
2025-07-03 09:44:39 +02:00
parent 849302fb3f d92e4c2695
commit 1dfae2747f
2 changed files with 38 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
scripts/tts_mlx.py
View File

@@ -2,7 +2,7 @@
# requires-python = ">=3.12"
# dependencies = [
# "huggingface_hub",
# "moshi_mlx>=0.2.8",
# "moshi_mlx @ git+https://git@github.com/kyutai-labs/moshi#egg=moshi_mlx&subdirectory=moshi_mlx",
# "numpy",
# "sounddevice",
# ]
@@ -142,10 +142,10 @@ def main():
wav_frames = queue.Queue()
def _on_audio_hook(audio_tokens):
if (audio_tokens == -1).any():
def _on_frame(frame):
if (frame == -1).any():
return
_pcm = tts_model.mimi.decode_step(audio_tokens[None, :, None])
_pcm = tts_model.mimi.decode_step(frame[:, :, None])
_pcm = np.array(mx.clip(_pcm[0, 0], -1, 1))
wav_frames.put_nowait(_pcm)
@@ -157,7 +157,7 @@ def main():
all_attributes,
cfg_is_no_prefix=cfg_is_no_prefix,
cfg_is_no_text=cfg_is_no_text,
on_audio_hook=_on_audio_hook,
on_frame=_on_frame,
)
frames = mx.concat(result.frames, axis=-1)
total_duration = frames.shape[0] * frames.shape[-1] / mimi.frame_rate
@@ -188,6 +188,7 @@ def main():
break
time.sleep(1)
else:
run()
frames = []
while True:
try: