whisper-tiny-mlx-safetensors

This model was converted to safetensors format from mlx-community/whisper-tiny-mlx.

The weights are split between the encoder (encoder.safetensors) and the decoder (decoder.safetensors).

Use with mlx-swift

import MLX
import MLXNN

let encoderUrl = URL(fileURLWithPath: "path/to/whisper-tiny-mlx-safetensors/encoder.safetensors")
let arrays = try MLX.loadArrays(url: encoderUrl)
let encoderParams = ModuleParameters.unflattened(arrays)
// Create the model and load the parameters
Downloads last month
4
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model’s pipeline type.