Spaces

·

The AI App Directory

New Space Get PRO Learn more

Open ASR Leaderboard

Compare speech‑to‑text models across datasets

Open Universal Arabic Asr Leaderboard

A benchmark for open-source multi-dialect Arabic ASR models

Nawah-ASR-60M-Max-Arabic

Arabic ASR, 62.7M params, 29.86 avg WER, 4th of 38

Turkish Asr Leaderboard

Explore Turkish ASR model rankings and benchmarks

Qwen3 ASR Demo

Convert uploaded audio to text with language detection

Fun-ASR-Nano

LLM-powered ASR: 31 languages, Chinese dialects, timestamps

CrisperWhisper 2.0 Controllable ASR

Verbatim + intended transcripts with word-level timing

ArmBench-ASR: Benchmarking Speech-to-Text Models on Armenian

Compare Armenian speech‑to‑text model performance

Niagara ASR Demo

Transcribe speech with tiny models running on a CPU, no GPU

IndicVoices ASR Explorer

Burmese ASR - Conformer

Transcribe Burmese speech to text instantly

Falcon ASR Demo

Transcribe up to 60‑second audio clips into text

Nemotron ASR Streaming — Persian

Streaming Persian (Farsi) speech recognition

Persian ASR

Espnet2_asr

Hindi_ASR

ASR Ukrainian

Italian Robust ASR

Wav2vec2 Vi Asr

Luganda ASR

Multilingual ASR

ESPNet2 ASR Librispeech Conformer (100h)

Arabic Asr

Asr_model