ModelListedExternal

Amnesiac Voxcpm LoRA

Single-speaker LoRA adapter selected from checkpoint step 90 after human listening on 110 curated A.M.N. voice clips.

Sourcehuggingface.co/hetanshwaghela/amnesiac-voxcpm-lora/tree/07d84393175e8486f0fb60053243866f1f55b89c

KindLoRABase modelopenbmb/VoxCPM1.5Versionlora_weights

Model source

Kind: LoRA
File size: 15.7 MB
Base model: openbmb/VoxCPM1.5
Version: vlora_weights
Updated: Sep 13, 2026
Downloads: 0
Source: Hugging Face

Source description

A.M.N. VoxCPM1.5 LoRA

Single-speaker LoRA adapter selected from checkpoint step 90 after human listening on 110 curated A.M.N. voice clips.

Base model: openbmb/VoxCPM1.5
LoRA: LM + DiT, rank 16, alpha 32
Native output: 44.1 kHz
Intended use: the AMNESIAC fictional interrogator voice

Synthetic speech should be disclosed where appropriate. Do not use this adapter for impersonation, fraud, or disinformation.

Sources

1 source

Hugging FacePrimaryVersion 07d84393175e8486f0fb60053243866f1f55b89c

huggingface.co/hetanshwaghela/amnesiac-voxcpm-lora/tree/07d84393175e8486f0fb60053243866f1f55b89c

Verified Sep 13

Model artifacts

1 artifact

lora_weights.safetensors

safetensors · 15.7 MB · SHA-256 dddfa755e943…6e83 · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 13huggingface.co/hetanshwaghela/amnesiac-voxcpm-lora

--- base_model: openbmb/VoxCPM1.5 library_name: voxcpm pipeline_tag: text-to-speech tags: - lora - voxcpm - text-to-speech --- # A.M.N. VoxCPM1.5 LoRA Single-speaker LoRA adapter selected from checkpoint step 90 after human listening on 110 curated A.M.N. voice clips. - Base model: `openbmb/VoxCPM1.5` - LoRA: LM + DiT, rank 16, alpha 32 - Native output: 44.1 kHz - Intended use: the AMNESIAC fictional interrogator voice Synthetic speech should be disclosed where appropriate. Do not use this adapter for impersonation, fraud, or disinformation.