deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

set use_spk2info_cache=False

Browse Source
This commit is contained in:
yuekaiz
2025-09-05 14:03:23 +08:00
parent 6971536358
commit 8ded65e611
2 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
runtime/triton_trtllm/README.md
View File

@@ -84,6 +84,8 @@ The following results were obtained by decoding on a single L20 GPU with 26 prom
| Streaming, use_spk2info_cache=True | 2 | 323.04 | 316.83 | 0.0905 | | Streaming, use_spk2info_cache=True | 2 | 323.04 | 316.83 | 0.0905 |
| Streaming, use_spk2info_cache=True | 4 | 977.68 | 903.68| 0.0733 | | Streaming, use_spk2info_cache=True | 4 | 977.68 | 903.68| 0.0733 |
> If your service only needs a fixed speaker, you can set `use_spk2info_cache=True` in `run.sh`. To add more speakers, refer to the instructions [here](https://github.com/qi-hua/async_cosyvoice?tab=readme-ov-file#9-spk2info-%E8%AF%B4%E6%98%8E).
**Offline TTS (Full Sentence Latency)** **Offline TTS (Full Sentence Latency)**
| Mode | Note | Concurrency | Avg Latency (ms) | P50 Latency (ms) | RTF | | Mode | Note | Concurrency | Avg Latency (ms) | P50 Latency (ms) | RTF |
|---|---|---|---|---|---| |---|---|---|---|---|---|

2
runtime/triton_trtllm/run.sh
View File

@@ -15,7 +15,7 @@ trt_engines_dir=./trt_engines_${trt_dtype}
model_repo=./model_repo_cosyvoice2 model_repo=./model_repo_cosyvoice2
use_spk2info_cache=True use_spk2info_cache=False
if [ $stage -le -1 ] && [ $stop_stage -ge -1 ]; then if [ $stage -le -1 ] && [ $stop_stage -ge -1 ]; then
echo "Cloning CosyVoice" echo "Cloning CosyVoice"