-
Is it possiable for Whisper to support Hotwords?
-
目前都返回错误码-412，请求被拦截
-
Hey,
Im trying to change voice for my raspOVOS.
I modified /etc/mycroft/mycroft.conf to be following
```json
{
"enable_old_audioservice": false,
"logs": {
"path": "/ramdis…
-
How to solve the issue of 'measure_cfg' and 'method_cfg'?
When loading the model using the text_to_speech_eval.py script the model instantiation fails:
[NeMo E 2024-06-02 11:21:20 common:529] Mo…
-
## 🐛 Bug
### To Reproduce
from funasr import AutoModel
model = AutoModel(model="paraformer-zh", model_revision="v2.0.4",
vad_model="fsmn-vad", vad_model_re…
-
```
Mar 27 19:15:15 neon ovos-dinkum-listener[955]: 2024-03-27 19:15:15.391 - voice - ovos_dinkum_listener.voice_loop.voice_loop:run:231 - INFO - Wakeword detected
Mar 27 19:15:17 neon ovos-dinkum-l…
-
## ❓ Questions and Help
I found that: in function load_pretrained_model:
logging.debug("Loaded src_state keys: {}".format(src_state.keys()))
logging.debug("Loaded dst_state keys: {}".format(dst_s…
-
## 🐛 Bug
### To Reproduce
pt模型测试代码：
model = AutoModel(model="model_zoo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.4",
vad_model…
-
This is the schema:
```
generator client {
provider = "prisma-client-js"
previewFeatures = ["extendedIndexes", "fullTextIndex"]
}
datasource db {
provider = "mysql"
url =…
-
## Feature
Syllable level VAD for mandarin, to segment every syllables of mandarin voice
## Motivation
Typically every mandarin syllable cost the same fixed 0.3 seconds,
every mandarin syllabl…