bin模型文件支持在whisper.cpp中运行吗？
#3
by
telehan
- opened
尝试用 https://github.com/ggerganov/whisper.cpp 运行 bin 模型文件，提示如下问题
whisper_init_from_file_with_params_no_state: loading model from '~/github/whisper.cpp/models/Belle-whisper-large-v3-turbo-zh.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
whisper_model_load: loading model
whisper_model_load: invalid model data (bad magic)
whisper_init_with_params_no_state: failed to load model
error: failed to initialize whisper context
尝试convert-pt-to-ggml.py转换为ggml出现如下问题
$python3.11 models/convert-pt-to-ggml.py ~/Workspace/huggingface/Belle-whisper-large-v3-turbo-zh/pytorch_model.bin ~/Workspace/github/whisper.cpp ~/Workspace/huggingface/Belle-whisper-large-v3-turbo-zh/ggml_model.bin
~/Workspace/github/whisper.cpp/models/convert-pt-to-ggml.py:205: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(fp, map_location="cpu")
Traceback (most recent call last):
File "~/Workspace/github/whisper.cpp/models/convert-pt-to-ggml.py", line 210, in <module>
hparams = checkpoint["dims"]
~~~~~~~~~~^^^^^^^^
KeyError: 'dims'
@telehan 解决了么？
ggml model is here :
https://huggingface.co/BELLE-2/Belle-whisper-large-v3-turbo-zh-ggml