cvlab-kaist / GaussianTalker

Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko, Sangjun Ahn and Seungryong Kim
Other
295 stars 36 forks source link

Error when Inference with custom audio #24

Closed rawrshah closed 5 months ago

rawrshah commented 5 months ago

Hello!

Having error while Inferencing with custom audio.

total frame: 449 [20/06 12:24:24] FPS: 97.33466045638134 [20/06 12:24:24] Traceback (most recent call last): File "render.py", line 233, in render_sets(model.extract(args), hyperparam.extract(args), args.iteration, pipeline.extract(args), args) File "render.py", line 168, in render_sets render_set(dataset.model_path, "custom", scene.loaded_iter, scene.getCustomCameras(), gaussians, pipeline, audio_dir, batch_size) File "render.py", line 137, in render_set cmd = f'ffmpeg -loglevel quiet -y -i {render_path}/renders.mp4 -i {inf_audio_dir} -c:v copy -c:a aac {render_path}/{modelpath.split("/")[-2]}{name}_{iteration}iter_renders.mov' IndexError: list index out of range

What may cause this error?

justin4ai commented 4 months ago

Hello, do you have any clue about this? I am facing the same error.

rawrshah commented 4 months ago

@justin4ai if I remember correctly, issue was with slash symbols while running script. Try running python train.py -s ${YOUR_DATASET_DIR}//${DATASET_NAME} --model_path ${YOUR_MODEL_DIR} --configs arguments/64_dim_1_transformer.py --iteration 10000 --batch 128 instead of python train.py -s ${YOUR_DATASET_DIR}/${DATASET_NAME} --model_path ${YOUR_MODEL_DIR} --configs arguments/64_dim_1_transformer.py --iteration 10000 --batch 128

justin4ai commented 4 months ago

Oh yeah it was related to the path although my solution was a bit different with yours! Now the error is gone. Appreciate your help friend :)

liushh39 commented 4 months ago

Oh yeah it was related to the path although my solution was a bit different with yours! Now the error is gone. Appreciate your help friend :) so how you sovle this?

liushh39 commented 4 months ago

@justin4ai if I remember correctly, issue was with slash symbols while running script. Try running python train.py -s ${YOUR_DATASET_DIR}//${DATASET_NAME} --model_path ${YOUR_MODEL_DIR} --configs arguments/64_dim_1_transformer.py --iteration 10000 --batch 128 instead of python train.py -s ${YOUR_DATASET_DIR}/${DATASET_NAME} --model_path ${YOUR_MODEL_DIR} --configs arguments/64_dim_1_transformer.py --iteration 10000 --batch 128

it does not work for me