使用Whisper-large-v3和cam++的组合报错

[MJ666-K]

from funasr import AutoModel
import time

wav_file = "/mnt/data/toolbox_dir/voice_trans/test-file/vad_example.wav"

model = AutoModel(
model="/mnt/data/toolbox_dir/voice_trans/Whisper-large-v3",
vad_model="/mnt/data/toolbox_dir/voice_trans/speech_fsmn_vad_zh-cn-16k-common-pytorch",
vad_kwargs={"max_single_segment_time": 30000},
punc_model="/mnt/data/toolbox_dir/voice_trans/punc_ct-transformer_cn-en-common-vocab471067-large",
spk_model="/mnt/data/toolbox_dir/voice_trans/speech_campplus_sv_zh-cn_16k-common",
device='cuda:2'
)

start_time = time.time()

res = model.generate(
input=wav_file,
batch_size_s=300,
batch_size=1
)

---

Why is it reported wrong? Please help me check it.

---

File "/root/anaconda3/lib/python3.12/runpy.py", line 198, in _run_module_as_main
return _run_code(code, main_globals, None,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/anaconda3/lib/python3.12/runpy.py", line 88, in _run_code
exec(code, run_globals)
File "/root/.vscode-server/extensions/ms-python.debugpy-2024.12.0/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/main.py", line 71, in
cli.main()
File "/root/.vscode-server/extensions/ms-python.debugpy-2024.12.0/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 501, in main
run()
File "/root/.vscode-server/extensions/ms-python.debugpy-2024.12.0/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 351, in run_file
runpy.run_path(target, run_name="main")
File "/root/.vscode-server/extensions/ms-python.debugpy-2024.12.0/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 310, in run_path
return _run_module_code(code, init_globals, run_name, pkg_name=pkg_name, script_name=fname)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.vscode-server/extensions/ms-python.debugpy-2024.12.0/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 127, in _run_module_code
_run_code(code, mod_globals, init_globals, mod_name, mod_spec, pkg_name, script_name)
File "/root/.vscode-server/extensions/ms-python.debugpy-2024.12.0/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 118, in _run_code
exec(code, run_globals)
File "/mnt/data/toolbox_dir/voice_trans/test.py", line 25, in
res = model.generate(
^^^^^^^^^^^^^^^
File "/mnt/data/toolbox_dir/voice_trans/venv/lib/python3.12/site-packages/funasr/auto/auto_model.py", line 304, in generate
return self.inference_with_vad(input, input_len=input_len, **cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/data/toolbox_dir/voice_trans/venv/lib/python3.12/site-packages/funasr/auto/auto_model.py", line 554, in inference_with_vad
sv_output = postprocess(all_segments, None, labels, spk_embedding.cpu())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/data/toolbox_dir/voice_trans/venv/lib/python3.12/site-packages/funasr/models/campplus/utils.py", line 117, in postprocess
assert len(segments) == len(labels)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError
0%| | 0/1 [00:46<?, ?it/s]