deepgeek/MiniCPM-o
2
0
Fork 0
mirror of https://github.com/OpenBMB/MiniCPM-V.git synced 2026-02-04 17:59:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

add model init in Multimodal Live Streaming code (#733)

Browse Source
This commit is contained in:
YuzaChongyi
2025-01-16 20:20:58 +08:00
committed by GitHub
parent 2c0e7ff051
commit 5520d436ed
2 changed files with 30 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@@ -2197,8 +2197,8 @@ from moviepy.editor import VideoFileClip
import tempfile import tempfile
import librosa import librosa
import soundfile as sf import soundfile as sf
import torch
## make sure The model has been initialized and `model.init_tts()` has been executed from transformers import AutoModel, AutoTokenizer
def get_video_chunk_content(video_path, flatten=True): def get_video_chunk_content(video_path, flatten=True):
video = VideoFileClip(video_path) video = VideoFileClip(video_path)
@@ -2223,7 +2223,19 @@ def get_video_chunk_content(video_path, flatten=True):
return contents return contents
video_path="/path/to/video"
model = AutoModel.from_pretrained('openbmb/MiniCPM-o-2_6', trust_remote_code=True,
attn_implementation='sdpa', torch_dtype=torch.bfloat16)
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-o-2_6', trust_remote_code=True)
model.init_tts()
# If you are using an older version of PyTorch, you might encounter this issue "weight_norm_fwd_first_dim_kernel" not implemented for 'BFloat16', Please convert the TTS to float32 type.
# model.tts.float()
# https://huggingface.co/openbmb/MiniCPM-o-2_6/blob/main/assets/Skiing.mp4
video_path="assets/Skiing.mp4"
sys_msg = model.get_sys_prompt(mode='omni', language='en') sys_msg = model.get_sys_prompt(mode='omni', language='en')
# if use voice clone prompt, please set ref_audio # if use voice clone prompt, please set ref_audio
# ref_audio_path = '/path/to/ref_audio' # ref_audio_path = '/path/to/ref_audio'

18
README_zh.md
View File

@@ -2179,8 +2179,8 @@ from moviepy.editor import VideoFileClip
import tempfile import tempfile
import librosa import librosa
import soundfile as sf import soundfile as sf
import torch
## make sure The model has been initialized and `model.init_tts()` has been executed from transformers import AutoModel, AutoTokenizer
def get_video_chunk_content(video_path, flatten=True): def get_video_chunk_content(video_path, flatten=True):
video = VideoFileClip(video_path) video = VideoFileClip(video_path)
@@ -2205,7 +2205,19 @@ def get_video_chunk_content(video_path, flatten=True):
return contents return contents
video_path="/path/to/video"
model = AutoModel.from_pretrained('openbmb/MiniCPM-o-2_6', trust_remote_code=True,
attn_implementation='sdpa', torch_dtype=torch.bfloat16)
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-o-2_6', trust_remote_code=True)
model.init_tts()
# If you are using an older version of PyTorch, you might encounter this issue "weight_norm_fwd_first_dim_kernel" not implemented for 'BFloat16', Please convert the TTS to float32 type.
# model.tts.float()
# https://huggingface.co/openbmb/MiniCPM-o-2_6/blob/main/assets/Skiing.mp4
video_path="assets/Skiing.mp4"
sys_msg = model.get_sys_prompt(mode='omni', language='en') sys_msg = model.get_sys_prompt(mode='omni', language='en')
# if use voice clone prompt, please set ref_audio # if use voice clone prompt, please set ref_audio
# ref_audio_path = '/path/to/ref_audio' # ref_audio_path = '/path/to/ref_audio'