Add model card
c842bc9 verified - compiled-encoder-4bit.mlmodelc Upload coremldata.bin
- compiled-encoder-4bit.mlmodelc_encrypted Upload coremldata.bin.enc
- 1.83 kB Upload processor.pkl.enc
- 776 Bytes Add model card
empty_hf_model.pkl Detected Pickle imports (11)
- "asr_streaming.modules.hf_asr_wrapper.OptimizedWhisperForConditionalGeneration",
- "transformers.generation.configuration_utils.GenerationConfig",
- "transformers.models.whisper.modeling_whisper.WhisperModel",
- "collections.OrderedDict",
- "transformers.generation.configuration_utils.CompileConfig",
- "torch.float32",
- "torch._utils._rebuild_parameter",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.linear.Identity",
- "torch.storage._load_from_bytes",
- "transformers.models.whisper.configuration_whisper.WhisperConfig"
How to fix it?
6.93 kB Upload HF model template - 6.96 kB Upload empty_hf_model.pkl.enc
mlx_decoder_4bit.pkl Detected Pickle imports (10)
- "asr_streaming.modules.mlx_whisper_model.ResidualAttentionBlock",
- "numpy.dtype",
- "mlx.core.array",
- "mlx.nn.layers.quantized.QuantizedLinear",
- "asr_streaming.modules.mlx_whisper_model.MultiHeadAttention",
- "mlx.nn.layers.normalization.LayerNorm",
- "mlx.nn.layers.embedding.Embedding",
- "numpy._core.multiarray._reconstruct",
- "numpy.ndarray",
- "asr_streaming.modules.mlx_whisper_model.TextDecoder"
How to fix it?
335 MB Upload decoder model - 335 MB Upload mlx_decoder_4bit.pkl.enc
processor.pkl Detected Pickle imports (9)
- "transformers.models.whisper.processing_whisper.WhisperProcessor",
- "numpy.dtype",
- "numpy.ndarray",
- "regex._regex.compile",
- "tokenizers.AddedToken",
- "transformers.models.whisper.feature_extraction_whisper.WhisperFeatureExtractor",
- "transformers.tokenization_utils.Trie",
- "numpy.core.multiarray._reconstruct",
- "transformers.models.whisper.tokenization_whisper.WhisperTokenizer"
How to fix it?
2.43 MB Upload processor - 2.43 MB Upload processor.pkl.enc
