#5896 语音识别阶段出错[Qwen-ASR(本地内置)] CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasGemmEx( handle, opa, opb, m, n,

语音识别阶段出错[Qwen-ASR(本地内置)] CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasGemmEx( handle, opa, opb, m, n, k, alpha_ptr, a, CUDA_R_16F, lda, b, CUDA_R_16F, ldb, beta_ptr, c, CUDA_R_16F, ldc, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP):Traceback (most recent call last):
File "videotrans\process\_stt_qwen.py", line 48, in qwen3asr_fun
File "D:\AISPWIN401\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "qwen_asr\inference\qwen3_asr.py", line 383, in transcribe

raw_outputs = self._infer_asr(chunk_ctx, chunk_wavs, chunk_lang)

File "qwen_asr\inference\qwen3_asr.py", line 485, in _infer_asr

return self._infer_asr_transformers(contexts, wavs, languages)

File "qwen_asr\inference\qwen3_asr.py", line 510, in _infer_asr_transformers

text_ids = self.model.generate(**inputs, max_new_tokens=self.max_new_tokens)

File "D:\AISPWIN401\_internal\torch\utils\_contextlib.py", line 116, in decorate_con
......
otrans\task\job.py", line 100, in process_task

File "videotrans\task\speech2text.py", line 97, in recogn

File "videotrans\recognition\__init__.py", line 205, in run

File "videotrans\recognition\_base.py", line 91, in run

File "videotrans\recognition\_qwenasrlocal.py", line 45, in _exec

File "videotrans\configure\base.py", line 272, in _new_process

videotrans.configure.excepts.VideoTransError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasGemmEx( handle, opa, opb, m, n, k, alpha_ptr, a, CUDA_R_16F, lda, b, CUDA_R_16F, ldb, beta_ptr, c, CUDA_R_16F, ldc, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP):Traceback (most recent call last):
File "videotrans\process\_stt_qwen.py", line 48, in qwen3asr_fun
File "D:\AISPWIN401\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "qwen_asr\inference\qwen3_asr.py", line 383, in transcribe

raw_outputs = self._infer_asr(chunk_ctx, chunk_wavs, chunk_lang)

File "qwen_asr\inference\qwen3_asr.py", line 485, in _infer_asr

return self._infer_asr_transformers(contexts, wavs, languages)

File "qwen_asr\inference\qwen3_asr.py", line 510, in _infer_asr_transformers

text_ids = self.model.generate(**inputs, max_new_tokens=self.max_new_tokens)

File "D:\AISPWIN401\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "qwen_asr\core\transformers_backend\modeling_qwen3_asr.py", line 1353, in generate

thinker_result = self.thinker.generate(input_ids=input_ids, return_dict_in_generate=True, **thinker_kwargs)

File "D:\AISPWIN401\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\AISPWIN401\_internal\transformers4576\generation\utils.py", line 2566, in generate

result = decoding_method(

File "D:\AISPWIN401\_internal\transformers4576\generation\utils.py", line 2786, in _sample

outputs = self(**model_inputs, return_dict=True)

File "D:\AISPWIN401\_internal\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

File "D:\AISPWIN401\_internal\torch\nn\modules\module.py", line 1762, in _call_impl

return forward_call(*args, **kwargs)

File "D:\AISPWIN401\_internal\transformers4576\utils\generic.py", line 918, in wrapper

output = func(self, *args, **kwargs)

File "qwen_asr\core\transformers_backend\modeling_qwen3_asr.py", line 1241, in forward

logits = self.lm_head(hidden_states)

File "D:\AISPWIN401\_internal\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

File "D:\AISPWIN401\_internal\torch\nn\modules\module.py", line 1762, in _call_impl

return forward_call(*args, **kwargs)

File "D:\AISPWIN401\_internal\torch\nn\modules\linear.py", line 125, in forward

return F.linear(input, self.weight, self.bias)

RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasGemmEx( handle, opa, opb, m, n, k, alpha_ptr, a, CUDA_R_16F, lda, b, CUDA_R_16F, ldb, beta_ptr, c, CUDA_R_16F, ldc, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP)
cfg=TaskCfgSTT(uuid='f920497220', name='D:/00803.m4a', dirname='D:/', noextname='00803', basename='00803.m4a', ext='m4a', target_dir='D:/AIOUT/recogn', cache_folder='D:/AISPWIN401/tmp/17204/f920497220', is_cuda=True, source_language=None, source_language_code=None, source_sub=None, source_wav=None, source_wav_output=None, target_language=None, target_language_code=None, target_sub='D:/AIOUT/recogn/00803.srt', target_wav=None, target_wav_output=None, detect_language='zh-cn', recogn_type=2, model_name='1.7B', shibie_audio='D:/AISPWIN401/tmp/17204/f920497220/00803-1784340394.8178532.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0)