Traceback (most recent call last):
File "/root/miniconda3/envs/sensevoice/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/root/miniconda3/envs/sensevoice/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/data2/workspace/egs_vocal_extractor/data/speech_det.py", line 156, in process_audio_task
res = model.generate(
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 306, in generate
return self.inference_with_vad(input, input_len=input_len, **cfg)
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 464, in inference_with_vad
results = self.inference(
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 345, in inference
res = model.inference(**batch, **kwargs)
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/models/sense_voice/model.py", line 950, in inference
timestamp = self.post(timestamp)
File "/root/miniconda3/envs/sensevoice/lib/python3.10/site-packages/funasr/models/sense_voice/model.py", line 973, in post
elif prev_word.isalpha() and prev_word.isascii() and word.isalpha() and word.isascii():
AttributeError: 'NoneType' object has no attribute 'isalpha'
* fix: use converted token_ids for alignment
BPE doesn't guarantee converted ids (subwords) are revertible. which means `tokens` converted back is not always the same as `token_int`. A easy fix is to directly use the converted ids for alignment. Since they are from the same text, it shouldn't matter.
* fix: handle empty string
to index an empty string is to raise an exception. 这里没有判空。
Fixed a bug that caused a runtime error when running the model on CPU, which was introduced in commit c1e365fea0. The error was related to incorrect handling of device placement.
"/Users/{USER}/.pyenv/versions/funasr_usage/lib/python3.12/site-packages/funasr/utils/postprocess_utils.py", line 127, in abbr_dispose
end = time_stamp[ts_nums[num]][1]
~~~~~~~~~~^^^^^^^^^^^^^^
IndexError: list index out of range
- In GetFrameState(), pass generator to sum() instead of generating a list, ~10% gain in a 21s sample
- In GetFrameState(), cast `sum_score` (a tensor) to float to reduce calling to tensor lib,
~13% gain in a 23s example
- In PopDataToOutputBuf(), remove unused `out_pos` and related calculation, ~10% gain in a 27s sample
