[Feat]Support voice clone for omnivoice in online serving & add seed parameter for reproducible (#3668)
Signed-off-by: sphinxkkkbc <binchengkang8@gmail.com> Co-authored-by: sphinxkkkbc <binchengkang8@gmail.com>
This commit is contained in:
1 parent
c69ed4037d
commit
4d9262a6eb
9 files changed
+158
-22
No files matched your search
@@ -271,6 +271,14 @@ python examples/offline_inference/text_to_speech/omnivoice/end2end.py \
|
||||
--lang zh
|
||||
```
|
||||
|
||||
### Seed for Reproducibility
|
||||
```bash
|
||||
python examples/offline_inference/text_to_speech/omnivoice/end2end.py \
|
||||
--model k2-fsa/OmniVoice \
|
||||
--text "Hello, this is a test." \
|
||||
--seed 42
|
||||
```
|
||||
|
||||
### Notes
|
||||
- Stage 0 (Generator): Qwen3-0.6B with 32-step iterative unmasking.
|
||||
- Stage 1 (Decoder): HiggsAudioV2 RVQ + DAC at 24 kHz.
|
||||
|
||||
@@ -80,6 +80,12 @@ def run_e2e():
|
||||
default=600,
|
||||
help="Stage initialization timeout in seconds",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--seed",
|
||||
type=int,
|
||||
default=None,
|
||||
help="Random seed for generation",
|
||||
)
|
||||
nullify_stage_engine_defaults(parser)
|
||||
args = parser.parse_args()
|
||||
|
||||
@@ -122,7 +128,7 @@ def run_e2e():
|
||||
if mm_processor_kwargs:
|
||||
prompts["mm_processor_kwargs"] = mm_processor_kwargs
|
||||
|
||||
sampling_params_list = [OmniDiffusionSamplingParams()]
|
||||
sampling_params_list = [OmniDiffusionSamplingParams(extra_args={"seed": args.seed})]
|
||||
|
||||
print(f"Generating speech for: {args.text}")
|
||||
|
||||
|
||||
Reference in new issue
Block a user