mirror of
https://github.com/BoardWare-Genius/jarvis-models.git
synced 2025-12-13 16:53:24 +00:00
137 lines
4.3 KiB
Markdown
137 lines
4.3 KiB
Markdown
# jarvis-models
|
|
## Conda Environment and Python Library Requirement
|
|
```bash
|
|
conda create -n jarvis-models python==3.10.11
|
|
pip install -r sample/requirement_out_of_pytorch.txt
|
|
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118
|
|
```
|
|
## More Dependencies
|
|
| System | package | web | install command |
|
|
| --- |-----------------------| --- | --- |
|
|
| python | filetype | https://pypi.org/project/filetype/ | pip install filetype |
|
|
| python | fastAPI | https://fastapi.tiangolo.com/ | pip install fastapi |
|
|
| python | python-multipart | https://pypi.org/project/python-multipart/ | pip install python-multipart |
|
|
| python | uvicorn | https://www.uvicorn.org/ | pip install "uvicorn[standard]" |
|
|
| python | SpeechRecognition | https://pypi.org/project/SpeechRecognition/ | pip install SpeechRecognition |
|
|
| python | gtts | https://pypi.org/project/gTTS/ | pip install gTTS |
|
|
| python | PyYAML | https://pypi.org/project/PyYAML/ | pip install PyYAML |
|
|
| python | injector | https://github.com/python-injector/injector | pip install injector |
|
|
| python | langchain | https://github.com/langchain-ai/langchain | pip install langchain |
|
|
| python | chromadb | https://docs.trychroma.com/getting-started | pip install chromadb |
|
|
| python | lagent | https://github.com/InternLM/lagent/blob/main/README.md | pip install lagent |
|
|
| python | sentence_transformers | https://github.com/InternLM/lagent/blob/main/README.md | pip install sentence_transformers |
|
|
|
|
|
|
## Start
|
|
Start the jarvis-models service via
|
|
```bash
|
|
uvicorn main:app --reload
|
|
```
|
|
or
|
|
```bash
|
|
python main.py
|
|
```
|
|
|
|
## Configuration
|
|
Create ".env.yaml" at the root of jarvis-models, and copy the following yaml configuration
|
|
```yaml
|
|
env:
|
|
version: 0.0.1
|
|
host: 0.0.0.0
|
|
port: 8000
|
|
|
|
log:
|
|
level: debug
|
|
time_format: "%Y-%m-%d %H:%M:%S"
|
|
filename: "D:/Workspace/Logging/jarvis/jarvis-models.log"
|
|
|
|
melotts:
|
|
mode: local # or docker
|
|
url: http://10.6.44.141:18080/convert/tts
|
|
speed: 0.9
|
|
device: 'cuda:0'
|
|
language: 'ZH'
|
|
speaker: 'ZH'
|
|
|
|
cosyvoicetts:
|
|
mode: local # or docker
|
|
url: http://10.6.44.141:18080/convert/tts
|
|
speed: 0.9
|
|
device: 'cuda:0'
|
|
language: '粤语女'
|
|
speaker: 'ZH'
|
|
|
|
sovitstts:
|
|
mode: docker
|
|
url: http://10.6.80.90:9880/tts
|
|
speed: 0.9
|
|
device: 'cuda:0'
|
|
language: 'ZH'
|
|
speaker: 'ZH'
|
|
text_lang: "yue"
|
|
ref_audio_path: "output/slicer_opt/Ricky-Wong/Ricky-Wong-3-Mins.wav_0006003840_0006134080.wav"
|
|
prompt_lang: "yue"
|
|
prompt_text: "你失敗咗點算啊？你而家安安穩穩，點解要咁樣做呢？"
|
|
text_split_method: "cut5"
|
|
batch_size: 1
|
|
media_type: "wav"
|
|
streaming_mode: True
|
|
|
|
sensevoiceasr:
|
|
mode: local # or docker
|
|
url: http://10.6.44.141:18080/convert/tts
|
|
speed: 0.9
|
|
device: 'cuda:0'
|
|
language: '粤语女'
|
|
speaker: 'ZH'
|
|
|
|
tesou:
|
|
url: http://120.196.116.194:48891/chat/
|
|
|
|
TokenIDConverter:
|
|
token_path: src/asr/resources/models/token_list.pkl
|
|
unk_symbol: <unk>
|
|
|
|
CharTokenizer:
|
|
symbol_value:
|
|
space_symbol: <space>
|
|
remove_non_linguistic_symbols: false
|
|
|
|
WavFrontend:
|
|
cmvn_file: src/asr/resources/models/am.mvn
|
|
frontend_conf:
|
|
fs: 16000
|
|
window: hamming
|
|
n_mels: 80
|
|
frame_length: 25
|
|
frame_shift: 10
|
|
lfr_m: 7
|
|
lfr_n: 6
|
|
filter_length_max: -.inf
|
|
dither: 0.0
|
|
|
|
Model:
|
|
model_path: src/asr/resources/models/model.onnx
|
|
use_cuda: false
|
|
CUDAExecutionProvider:
|
|
device_id: 0
|
|
arena_extend_strategy: kNextPowerOfTwo
|
|
cudnn_conv_algo_search: EXHAUSTIVE
|
|
do_copy_in_default_stream: true
|
|
batch_size: 3
|
|
blackbox:
|
|
lazyloading: true
|
|
|
|
vlms:
|
|
urls:
|
|
qwen_vl: http://10.6.80.87:8000
|
|
qwen2_vl: http://10.6.80.87:23333
|
|
qwen2_vl_72b: http://10.6.80.91:23333
|
|
|
|
path:
|
|
chroma_rerank_embedding_model: /media/verachen/e0f7a88c-ad43-4736-8829-4d06e5ed8f4f/model/BAAI
|
|
cosyvoice_path: /media/verachen/e0f7a88c-ad43-4736-8829-4d06e5ed8f4f/Workspace/CosyVoice
|
|
cosyvoice_model_path: /media/verachen/e0f7a88c-ad43-4736-8829-4d06e5ed8f4f/model/Voice/CosyVoice/pretrained_models
|
|
sensevoice_model_path: /media/verachen/e0f7a88c-ad43-4736-8829-4d06e5ed8f4f/model/Voice/SenseVoice/SenseVoiceSmall
|
|
```
|