LocalClaw/TTS/FastSLM-ASR
Local ASR model

FastSLM-ASR

Catalogue summary: Apache-licensed speech-language model specialized for efficient local ASR and long-form speech understanding. It adapts Qwen3-4B to audio with a hierarchical temporal abstractor, supports English and Korean transcription plus speech translation, summarization and spoken QA task tokens, and ships downloadable BF16/F32 safetensors with custom Transformers code.

Repository editorial metadata; verify comparative claims in the linked upstream material.

GPU recommendedspeech-to-text transcription2 languagesApache 2.0
Choose an app

Start with Recommended. No terminal commands are shown.

Compare speech models
Open model filesRecommended verified starting pointOpen in UnslothLaunches Unsloth Desktop on this modelOpen official projectApplication source and guided setupOpen on Hugging FaceFiles, licence and model cardCheck my machineOptional: verify the fit with your saved hardware

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Catalogue quality
9.2/10
Catalogue speed
7.8/10
Model size
5B params; 11.74 GB safetensors; upstream lists >=11.8 GB VRAM minimum
Voices
N/A (ASR and speech-language tasks: outputs text)

Can FastSLM-ASR run locally?

FastSLM-ASR can run locally for offline speech-to-text. Use the verified setup options on this page; no terminal command is required to choose the right path.

Apache 2.0 license. Still verify upstream usage notes before shipping.

Upstream source
multilinguallong-formcontrollable

Audio profile

Cat. quality
9.2
Cat. speed
7.8
Audio
8.8

Best fit

FastSLM-ASR is best for offline transcription, speech indexing and local voice pipelines.

Hardware: gpu

Model details

Type
Local ASR model
Family
fastslm
Latency
medium
Formats
transformerspytorchsafetensors
Languages
en, ko
Context
5B params, Qwen3-4B adaptation, English/Korean, ASR/AST/summarization/spoken QA task tokens, 16 kHz audio input, Open ASR leaderboard mean WER 5.91 and RTFx 77.56

Install locally

01
Check runtimeConfirm the backend supports transformers, pytorch, safetensors on your machine.
02
Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.
03
Test locallyRun a short private audio prompt before moving into production workflows.

Good for

  • speech-to-text transcription
  • GPU recommended local workflows
  • multilingual, long-form, controllable

Watch before shipping

  • Validate pronunciation, latency and artifacts with your own voice samples.
  • Review the upstream license and acceptable-use notes.
  • Benchmark on your target CPU, Apple Silicon or GPU setup.

Related TTS and speech models

OpenMOSS / MOSI.AI MOSS-Transcribe-Diarize 0.9B Local ASR model · Q 9.4 · Speed 8.4 IBM Granite Team Granite Speech 4.1 2B Plus Local ASR model · Q 9.3 · Speed 7.8 OpenMOSS / MOSI.AI MOSS-Audio 4B Instruct Local ASR model · Q 9.2 · Speed 7.7 FireRed Team FireRedAudio Local ASR model · Q 9.5 · Speed 6.6 ai-sage GigaChat Audio 10B A1.8B Local ASR model · Q 9.1 · Speed 6.7 KRAFTON AI A.X K2 Raon-Speech 21B-A3B Local ASR model · Q 9.4 · Speed 6.4 NVIDIA Parakeet TDT 0.6B v3 Local ASR model · Q 9.5 · Speed 9.7 NVIDIA Nemotron 3.5 ASR Streaming 0.6B Local ASR model · Q 9.4 · Speed 9.3
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw