Skip to content
ModelListedExternal
Download

Resemble Enhance

Resemble Enhance is an AI-powered tool that aims to improve the overall quality of speech by performing denoising and enhancement. It consists of two modules: a denoiser, which separates speech from a noisy audio,...

Sourcehuggingface.co/smcleod/resemble-enhance/tree/45f8dee36b802a38953894b33b49b843f42fdd5b
KindModelVersionMp rank 00 model statesCgrade

Model source

Kind
Model
File size
680 MB
Version
vMp rank 00 model states
Updated
Oct 30, 2026
Source
Hugging Face

Source description

Resemble Enhance is an AI-powered tool that aims to improve the overall quality of speech by performing denoising and enhancement. It consists of two modules: a denoiser, which separates speech from a noisy audio, and an enhancer, which further boosts the perceptual audio quality by restoring audio distortions and extending the audio bandwidth. The two models are trained on high-quality 44.1kHz speech data that guarantees the enhancement of your speech with high quality.

Below are three videos with separate examples of Resemble Enhance's denoiser module and then enhancer module improving speech quality.

Background Music - https://youtu.be/gl--IMtQ0XQ

Street Noise - https://youtu.be/zC87BjtsZVA

Archived Speech - https://youtu.be/6dALaLMJhSQ

Sources

1 source
Hugging FacePrimaryVersion 45f8dee36b802a38953894b33b49b843f42fdd5b
huggingface.co/smcleod/resemble-enhance/tree/45f8dee36b802a38953894b33b49b843f42fdd5b

Verified Oct 30

Model artifacts

1 artifact

enhancer_stage2/ds/G/default/mp_rank_00_model_states.pt

pt · 680 MB · SHA-256 f9d035f318de…d9d6 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 14huggingface.co/smcleod/resemble-enhance

--- license: mit language: - en pipeline_tag: audio-to-audio tags: - speech-enhancement - speech-denoising --- Resemble Enhance is an AI-powered tool that aims to improve the overall quality of speech by performing denoising and enhancement. It consists of two modules: a denoiser, which separates speech from a noisy audio, and an enhancer, which further boosts the perceptual audio quality by restoring audio distortions and extending the audio bandwidth. The two models are trained on high-quality 44.1kHz speech data that guarantees the enhancement of your speech with high quality. Below are three videos with separate examples of Resemble Enhance's denoiser module and then enhancer module improving speech quality. Background Music - https://youtu.be/gl--IMtQ0XQ Street Noise - https://youtu.be/zC87BjtsZVA Archived Speech - https://youtu.be/6dALaLMJhSQ

NoteAug 14huggingface.co/smcleod/resemble-enhance

Source context: 0 downloads · 0 likes · Pipeline audio-to-audio · Repo smcleod/resemble-enhance