---
title: acft-whisper-large-v3
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/acft-whisper-large-v3"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/acft-whisper-large-v3.md"
repository: AI-ModelScope/acft-whisper-large-v3
last_updated: 2025-11-18
license: apache-2.0
model_type:
  - whisper
architectures:
  - WhisperForConditionalGeneration
base_model:
  - openai/whisper-large-v3
base_model_relation: finetune
parameters: 1.5B
tensor_type:
  - F16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "vllm 0.9.2"
downloads: 75
stars: 0
---

# acft-whisper-large-v3

> acft-whisper-large-v3 - AI-ModelScope 在 ModelScope 开源的模型。This is in a fine-tuned series of OpenAI's Whisper models.

AI-ModelScope/acft-whisper-large-v3 是 ModelScope 魔搭社区上的 1.5B 参数机器学习模型，采用 apache-2.0 许可，基于 openai/whisper-large-v3 构建，可用 deploy_task vlm/text/emb、vllm 0.9.2 部署。

- **Repository**: AI-ModelScope/acft-whisper-large-v3
- **License**: apache-2.0
- **Parameters**: 1.5B
- **Base model**: openai/whisper-large-v3
- **Inference backends**: deploy_task vlm/text/emb, vllm 0.9.2
- **Downloads**: 75
- **Stars**: 0
- **Last updated**: 2025-11-18

Source: https://www.modelscope.cn/models/AI-ModelScope/acft-whisper-large-v3

---

# Model Card

## Model Description

This is in a fine-tuned series of [OpenAI's Whisper models](https://github.com/openai/whisper).

The models have been finetuned for dynamic audio context robustness, allowing shorter audio contexts for better performance with short audio inputs. The method is detailed [in our GitHub repo](https://github.com/futo-org/whisper-acft).

- **Developed by:** Mahmoud Ashraf inspired by FUTO
- **License:** Apache-2.0
- **Finetuned from model:** OpenAI Whisper

## Uses

These models are not useful by themselves under default Whisper runtime configurations.

The easiest way to test differing audio context is to use whisper.cpp with the `--audio-context` parameter. We provide converted whisper.cpp models in our [GitHub README](https://github.com/futo-org/whisper-acft?tab=readme-ov-file#finetuning-whisper-for-dynamic-audio-context-robustness).

## Metrics
Speed was evaluated using TensorRT-LLM using In-flight Batching
Dynamic context was padded with additional 128 context for stability

| Model Name                                                       | WER on Earnings22    | Relative Speed |
|------------------------------------------------------------------|--------|----------------|
| Large-V3 Full Context                                            | 15.283 | 1.0x           |
| Large-V3 Dynamic Context                                         | 17.515 | 2.1x           |
| This Model                                                       | 15.381 | 2.1x           |
| Large-V3 Turbo Full Context                                      | 15.373 | 1.9x           |
| Large-V3 Turbo Dynamic Context                                      | 62.921 | 6.4x           |
| [MahmoudAshraf/acft-whisper-large-v3-turbo](https://huggingface.co/MahmoudAshraf/acft-whisper-large-v3-turbo) | 15.605 | 5.1x           |

## Other Information

More information can be found in this [GitHub README](https://github.com/futo-org/whisper-acft?tab=readme-ov-file#finetuning-whisper-for-dynamic-audio-context-robustness).