whatmodel.sh

· find the best speech-to-text models you can run
178 models · scores combine 86 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][long-form transcription][multilingual transcription]
Filter by your hardware and budget
+ more
set[all sets][Open ASR English short-form WER (March 2026) · 176][LibriSpeech test-clean WER · 2]

Filter the model list while keeping overall scores. Models without a shared score scale are not yet calibrated; select a set to see its own scores.

Detect your exact chip or graphics card:

curl -G whatmodel.sh/stt -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/stt -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/stt -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

detecting your OS…

Run curl whatmodel.sh/sttto get this list in your terminal (add &format=json for agents).

ram[8][16][24][32][48][64][96][128][192][256]GB
gpu[apple silicon][graphics card][none]
price[local][$0.001][$0.002][$0.005][$0.01][any]max per audio min

detecting your OS…

Score vs API price

#modelscore↓where↓speed↓RAM↓get itsources
#modelscore↓where↓speed↓RAM↓get itsources
1Muse Voice Transcribe 1.0 Meta71±3*api $0.0030/audio mindeveloper.meta.com ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
2Grok Voice Transcribe 2.0 xAI70±3*api $0.0017/audio mindocs.x.ai ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
3Saarika v2.5 Sarvam AI70±5*comparison onlyBangla Speech-to-Text Benchmark v1.0 (Riverborn)
4Universal-3.6 Pro Realtime AssemblyAI70±3*api $0.0075/audio minwww.assemblyai.com ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
5Linden 1 (Agent STT) Speechmatics69±3*api $0.0050/audio minwww.speechmatics.com ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
6Soniox v5 Async Soniox68±5*api $0.0017/audio minsoniox.com ↗Bangla Speech-to-Text Benchmark v1.0 (Riverborn)
7Ink-2 Cartesia68±3*api $0.0065/audio mindocs.cartesia.ai ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
8Universal-3.5 Pro AssemblyAI67±3api $0.0035/audio minwww.assemblyai.com ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)verliapp/stt-benchmark · independent STT accuracy benchmarkCoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings (arXiv:2609.35645v1), Table 2
9Soniox v5 Real-Time Soniox67±3*api $0.0020/audio minsoniox.com ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
10Soniox v4 Real-Time Soniox67±3*comparison onlyPipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
11Gemini 3.5 Transcribe Google67±6*api $0.0050/audio minai.google.dev ↗Persian ASR Triple Threat Leaderboard (Reza2kn)
12Scribe v2 ElevenLabs66±1api $0.0037/audio minelevenlabs.io ↗Open ASR LeaderboardGigaSpeechBench: A Real-World Multilingual Speech-to-Text BenchmarkVoiceCodeBench (arXiv:2608.28916v2) · structured-token recovery ASR benchmarkCoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings (arXiv:2609.35645v1), Table 2BOTNOI Thai telephony ASR report (arXiv:2608.24916v1) · baseline CERsRW-Voice-EQ Bench (Hume AI)+9
13GPT Transcribe OpenAI64±4api $0.0045/audio mindevelopers.openai.com ↗VoiceCodeBench (arXiv:2608.28916v2) · structured-token recovery ASR benchmarkDanish Speech-to-Text Leaderboard (RyeAI) · results dataset
14Zoom Scribe v1 Zoom64±5*api price unknowndevelopers.zoom.us ↗Open ASR Leaderboard
15Granite Speech 5.0 470M TurboCTC NC IBM64±4*local~0.5GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
16Cohere Transcribe Arabic (07-2026) Cohere63±3local~4.1GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsQCRI Arabic + English ASR leaderboard (Hugging Face Space QCRI/AURA-Arabic-English-ASR-leaderboard)Open Universal Arabic ASR Leaderboard (Elm Research Center)
17Universal-3 Pro AssemblyAI63±2comparison onlyOpen ASR LeaderboardVoiceCodeBench (arXiv:2608.28916v2) · structured-token recovery ASR benchmarkRW-Voice-EQ Bench (Hume AI)
18Granite Speech 4.1 2B IBM62±3local~6GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsSwitch-aware evaluation of ASR on English-Yoruba code-switched speech (arXiv:2609.11786v1)
19Granite 4.0 1B Speech IBM62±3local~6GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR Leaderboard
20Granite Speech 5.0 470M TurboCTC IBM62±4*local~1.6GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
21MAI-Transcribe-1.5 Microsoft AI62±8*api $0.0060/audio minazure.microsoft.com ↗koedesk STT Bench v1 (Track A, FLEURS first-200)
22Fish Audio Transcribe 1 Fish Audio62±5api $0.0060/audio mindocs.fish.audio ↗verliapp/stt-benchmark · independent STT accuracy benchmark
23Inworld STT-1 Inworld62±6*api $0.0025/audio mindocs.inworld.ai ↗verliapp/stt-benchmark · independent STT accuracy benchmark
24Qwen-Audio-3.0-ASR Alibaba62±4*†comparison onlyQwen-Audio-3.0-ASR Technical Report (arXiv:2609.07549v2)
25Cohere Transcribe (03-2026) Cohere62±2api $0.0042/audio min +local~5.5GBfal.ai ↗Open ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsDutch ASR Leaderboard (tvosch) · committed result filesOpen Universal Arabic ASR Leaderboard (Elm Research Center)Quranic ASR Leaderboard (Quran-Lab, held-out recitation set)Dysarthric ASR with clinical context on the Speech Accessibility Project (arXiv:2605.02782v2)
26Granite Speech 4.1 2B NAR IBM62±4*local~2.5GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
27Nova-3 Deepgram61±2api $0.0052/audio mindevelopers.cloudflare.com ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)Russian STT benchmark by domainVoiceCodeBench (arXiv:2608.28916v2) · structured-token recovery ASR benchmarkBangla Speech-to-Text Benchmark v1.0 (Riverborn)verliapp/stt-benchmark · independent STT accuracy benchmarkCoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings (arXiv:2609.35645v1), Table 2+6
28Canary-Qwen-2.5B NVIDIA61±2local~6.6GBhow to run › NVIDIA ASR model cards (Parakeet / Canary, Hugging Face)AfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteOpen ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsRW-Voice-EQ Bench (Hume AI)Switch-aware evaluation of ASR on English-Yoruba code-switched speech (arXiv:2609.11786v1)
29Pulse (STT) Smallest.ai61±3*api $0.0040/audio mindocs.smallest.ai ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
30Scribe v1 ElevenLabs61±2comparison onlyOpen ASR LeaderboardBangla Speech-to-Text Benchmark v1.0 (Riverborn)verliapp/stt-benchmark · independent STT accuracy benchmarkOpen ASR Leaderboard – Chilean Spanish (idsudd / Alonso Astroza)
31Chirp 3 Google61±2api price unknowncloud.google.com ↗Open ASR LeaderboardAfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteGigaSpeechBench: A Real-World Multilingual Speech-to-Text BenchmarkVoiceCodeBench (arXiv:2608.28916v2) · structured-token recovery ASR benchmarkBOTNOI Thai telephony ASR report (arXiv:2608.24916v1) · baseline CERsRW-Voice-EQ Bench (Hume AI)+4
32Voxtral Small 24B (2507) Mistral61±2api $0.0040/audio min +local~59GBdocs.mistral.ai ↗Mistral AI — Voxtral technical reportOpen ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsCoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings (arXiv:2609.35645v1), Table 2Danish Speech-to-Text Leaderboard (RyeAI) · results datasetOpen Universal Arabic ASR Leaderboard (Elm Research Center)+1
33Gemini 3.5 Transcribe Live Google61±3*api $0.0090/audio minai.google.dev ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
34Granite Speech 4.1 2B Plus IBM61±4*local~2.4GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
35Parakeet TDT 0.6B v2 NVIDIA60±1local~1.9GBhow to run › NVIDIA ASR model cards (Parakeet / Canary, Hugging Face)AfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteOpen ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsmicrosoft/VibeVoice-ASR-BitNet model card (Accuracy table)Switch-aware evaluation of ASR on English-Yoruba code-switched speech (arXiv:2609.11786v1)+1
36Tencent Hy-ASR-3.0-preview Tencent60±4*comparison onlyQwen-Audio-3.0-ASR Technical Report (arXiv:2609.07549v2)
37Parakeet Unified EN 0.6B NVIDIA60±4*local~0.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
38Grok Voice Transcribe 1.0 xAI60±5comparison onlyverliapp/stt-benchmark · independent STT accuracy benchmark
39Qwen3-ASR-1.7B Alibaba (Qwen)60±1api $0.0005/audio min +local~3.3GBdeepinfra.com ↗Qwen/Qwen3-ASR-1.7B model cardOpen ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsGigaSpeechBench: A Real-World Multilingual Speech-to-Text BenchmarkMega-ASR (arXiv:2605.19833v1) · adverse-condition ASR baselines (CHiME-4, VOiCES, NOIZEUS)RW-Voice-EQ Bench (Hume AI)+10
40Canary-1B-Flash NVIDIA60±2local~4.4GBhow to run › AfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suitetranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR Leaderboard
41Granite Speech 3.3 2B IBM60±3local~7.7GBhow to run › AfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteOpen ASR Leaderboard
42Speechmatics Enhanced Speechmatics60±2api $0.0067/audio minwww.speechmatics.com ↗Open ASR Leaderboardverliapp/stt-benchmark · independent STT accuracy benchmarkRW-Voice-EQ Bench (Hume AI)Quranic ASR Leaderboard (Quran-Lab, held-out recitation set)
43Deepgram Nova 2 Deepgram60±4api $0.0058/audio mindeepgram.com ↗Russian STT benchmark by domain
44Fun-ASR-Flash Alibaba59±4*†comparison onlyQwen-Audio-3.0-ASR Technical Report (arXiv:2609.07549v2)
45Granite Speech 3.3 8B IBM59±5*local~21GBhow to run › Open ASR LeaderboardDysarthric ASR with clinical context on the Speech Accessibility Project (arXiv:2605.02782v2)
46Voxtral Mini Transcribe V2 Mistral59±3api $0.0030/audio mindocs.mistral.ai ↗Voxtral RealtimeDutch ASR Leaderboard (tvosch) · committed result fileskoedesk STT Bench v1 (Track A, FLEURS first-200)
47Avalon v1 (en) Aqua Voice59±5*comparison onlyOpen ASR Leaderboard
48GPT-Realtime-Whisper OpenAI59±3*api $0.017/audio mindevelopers.openai.com ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
49Canary-1B NVIDIA59±3local~5.3GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
50Parakeet Ultra Moondream59±3local~0.7GBhow to run › Moondream parakeet-ultra and parakeet-redux model cards (Benchmarks sections)transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
51Parakeet TDT 1.1B NVIDIA59±2local~5.8GBhow to run › AfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteOpen ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsDysarthric ASR with clinical context on the Speech Accessibility Project (arXiv:2605.02782v2)
52Voxtral Mini 3B (2507) Mistral58±1api $0.0010/audio min +local~12GBdeepinfra.com ↗Mistral AI — Voxtral technical reportOpen ASR LeaderboardAfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suitetranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsMega-ASR (arXiv:2605.19833v1) · adverse-condition ASR baselines (CHiME-4, VOiCES, NOIZEUS)Open ASR Leaderboard – Chilean Spanish (idsudd / Alonso Astroza)+5
53Universal-Streaming (English) AssemblyAI58±3*api $0.0025/audio minwww.assemblyai.com ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
54Parakeet RNNT 1.1B NVIDIA58±2local~5.6GBhow to run › NVIDIA ASR model cards (Parakeet / Canary, Hugging Face)AfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteOpen ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
55Chirp 2 Google58±3api price unknowncloud.google.com ↗Bangla Speech-to-Text Benchmark v1.0 (Riverborn)verliapp/stt-benchmark · independent STT accuracy benchmarkOpen ASR Leaderboard
56Canary-1B-v2 NVIDIA58±1local~5.2GBhow to run › NVIDIA ASR model cards (Parakeet / Canary, Hugging Face)Open ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsCanary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST (NVIDIA, arXiv:2509.14128v2)Mega-ASR (arXiv:2605.19833v1) · adverse-condition ASR baselines (CHiME-4, VOiCES, NOIZEUS)Open ASR Leaderboard – Chilean Spanish (idsudd / Alonso Astroza)+2
57Phi-4-multimodal-instruct Microsoft58±2local~14GBhow to run › Open ASR LeaderboardAfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteOpen ASR Leaderboard – Chilean Spanish (idsudd / Alonso Astroza)Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3Dysarthric ASR with clinical context on the Speech Accessibility Project (arXiv:2605.02782v2)
58Omnilingual ASR LLM 7B Meta58±2local~19GBhow to run › Open ASR LeaderboardOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)Open ASR Leaderboard – Chilean Spanish (idsudd / Alonso Astroza)Open Universal Arabic ASR Leaderboard (Elm Research Center)Quranic ASR Leaderboard (Quran-Lab, held-out recitation set)
59Omnilingual ASR LLM 7B v2 Meta58±3*local~19GBhow to run › Open ASR Leaderboard
60Distil-Whisper distil-large-v3.5 Hugging Face (Distil-Whisper)58±1local~2.3GBhow to run › distil-whisper/distil-large-v3.5 model cardAfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteOpen ASR LeaderboardRW-Voice-EQ Bench (Hume AI)
61Whisper large-v3-turbo OpenAI57±1api $0.0005/audio min +local~2.4GBdevelopers.cloudflare.com ↗distil-whisper/distil-large-v3.5 model cardOpen ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsverliapp/stt-benchmark · independent STT accuracy benchmarkLiteASR (arXiv:2502.20583v2) · ESB WER of Whisper and LiteASR-compressed encodersRussian ASR Leaderboard (ESpeech; benchmark by Nikolay Shmyrev)+7
62Omnilingual ASR LLM 3B Meta57±2local~11GBhow to run › Open ASR LeaderboardOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)Open Universal Arabic ASR Leaderboard (Elm Research Center)Quranic ASR Leaderboard (Quran-Lab, held-out recitation set)
63Fun-ASR-MLT-Nano-2512 Alibaba (FunAudioLLM)57±4local~0.9GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
64Parakeet Redux Moondream57±4†local~0.2GBhow to run › Moondream parakeet-ultra and parakeet-redux model cards (Benchmarks sections)
65Parakeet TDT 0.6B v3 NVIDIA57±1api $0.0015/audio min +local~2GBwww.together.ai ↗NVIDIA ASR model cards (Parakeet / Canary, Hugging Face)Open ASR LeaderboardMoondream parakeet-ultra and parakeet-redux model cards (Benchmarks sections)transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsCanary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST (NVIDIA, arXiv:2509.14128v2)Russian STT benchmark by domain+11
66Kyutai STT 2.6B (en) Kyutai57±4local~6.7GBhow to run › Voxtral RealtimeOpen ASR Leaderboard
67Whisper large-v3 OpenAI57±1api $0.0018/audio min +local~4.2GBconsole.groq.com ↗Mistral AI — Voxtral technical reportOpen ASR LeaderboardQwen/Qwen3-ASR-1.7B model carddistil-whisper/distil-large-v3.5 model cardAfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suitetranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports+25
68GLM-ASR-Nano-2512 Z.ai57±4local~5.9GBhow to run › Open ASR Leaderboardzai-org/GLM-ASR README benchmark table (GLM-ASR-Nano vs open/closed ASR)
69Parakeet RNNT 0.6B NVIDIA57±3local~3.5GBhow to run › Open ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
70Rev AI Fusion (Whisper Fusion) Rev57±4*comparison onlyOpen ASR Leaderboard
71Orukeet Oruk AI57±4*local~0.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
72Zipformer Transducer XL 290M SoundsGood AI56±5*†comparison onlyOpen ASR Leaderboard
73Parakeet TDT-CTC 1.1B NVIDIA56±4*local~1.3GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
74GPT-4o Mini Transcribe OpenAI56±2api $0.0030/audio mindevelopers.openai.com ↗Mistral AI — Voxtral technical reportVoxtral Realtimemu-bench: A Multilingual Utterance Transcription Benchmark (arXiv:2609.32082v1), Table 5Danish Speech-to-Text Leaderboard (RyeAI) · results dataset
75Omnilingual ASR LLM 1B v2 Meta56±3*local~6GBhow to run › Open ASR LeaderboardBenchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3
76Omnilingual ASR LLM 1B Meta56±2local~6GBhow to run › Open ASR LeaderboardOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)Open Universal Arabic ASR Leaderboard (Elm Research Center)Quranic ASR Leaderboard (Quran-Lab, held-out recitation set)
77Distil-Whisper distil-large-v3 Hugging Face (Distil-Whisper)56±2local~2.3GBhow to run › distil-whisper/distil-large-v3.5 model cardOpen ASR Leaderboardhuggingface/distil-whisper README (Distil-Whisper headline WER table)
78Omnilingual ASR LLM 3B v2 Meta56±3*local~11GBhow to run › Open ASR Leaderboard
79LiteWhisper large-v3 Efficient-Speech (LiteASR)55±3local~3.7GBhow to run › LiteASR (arXiv:2502.20583v2) · ESB WER of Whisper and LiteASR-compressed encodersOpen ASR Leaderboard
80Fun-ASR-Nano-2512 Alibaba (FunAudioLLM)55±3local~0.9GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsmicrosoft/VibeVoice-ASR-BitNet model card (Accuracy table)
81Scribe v2 Realtime ElevenLabs55±3*api $0.0065/audio minelevenlabs.io ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)
82LiteWhisper large-v3-acc Efficient-Speech (LiteASR)55±3local~3.9GBhow to run › LiteASR (arXiv:2502.20583v2) · ESB WER of Whisper and LiteASR-compressed encodersOpen ASR Leaderboard
83Omnilingual ASR CTC 3B v2 Meta55±3*local~7.9GBhow to run › Open ASR Leaderboard
84Omnilingual ASR CTC 7B Meta55±2local~16GBhow to run › Open ASR LeaderboardOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)Open Universal Arabic ASR Leaderboard (Elm Research Center)
85Parakeet CTC 1.1B NVIDIA55±3local~5.6GBhow to run › Open ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
86SeamlessM4T v2 Large Meta55±4local~9.2GBhow to run › Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST (NVIDIA, arXiv:2509.14128v2)ai-sage/GigaAM-Multilingual model card (Model Performance table)Danish Speech-to-Text Leaderboard (RyeAI) · results datasetOpen Universal Arabic ASR Leaderboard (Elm Research Center)Turkish ASR Leaderboard (TurkASR-Bench, yagmurtuncer)Quranic ASR Leaderboard (Quran-Lab, held-out recitation set)+1
87Qwen3-ASR-0.6B Alibaba (Qwen)55±1local~2.8GBhow to run › Qwen/Qwen3-ASR-1.7B model cardOpen ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsRW-Voice-EQ Bench (Hume AI)Persian ASR Triple Threat Leaderboard (Reza2kn)QCRI Arabic + English ASR leaderboard (Hugging Face Space QCRI/AURA-Arabic-English-ASR-leaderboard)+2
88Ink-Whisper Cartesia55±3api price unknowndocs.cartesia.ai ↗Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)verliapp/stt-benchmark · independent STT accuracy benchmark
89Breeze ASR 25 MediaTek Research54±4local~1.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
90Parakeet CTC 0.6B NVIDIA54±3local~3.4GBhow to run › Open ASR Leaderboardtranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
91Canary-180M-Flash NVIDIA54±3local~1.4GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR Leaderboard
92Omnilingual ASR CTC 3B Meta54±2local~7.9GBhow to run › Open ASR LeaderboardOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)Open Universal Arabic ASR Leaderboard (Elm Research Center)
93MOSS-Transcribe-Diarize 0.9B OpenMOSS54±4local~1GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
94GPT-4o Transcribe OpenAI53±1api $0.0060/audio mindevelopers.openai.com ↗Qwen/Qwen3-ASR-1.7B model cardAfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suitePipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)GigaSpeechBench: A Real-World Multilingual Speech-to-Text BenchmarkQwen-Audio-3.0-ASR Technical Report (arXiv:2609.07549v2)Bangla Speech-to-Text Benchmark v1.0 (Riverborn)+5
95LiteWhisper large-v3-turbo-acc Efficient-Speech (LiteASR)53±4*local~2.1GBhow to run › Open ASR LeaderboardLiteASR (arXiv:2502.20583v2) · ESB WER of Whisper and LiteASR-compressed encoders
96Voxtral Mini 4B Realtime (2602) Mistral53±2api $0.0060/audio min +local~3.2GBdocs.mistral.ai ↗Open ASR LeaderboardPipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README)Voxtral Realtimetranscribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsVibeVoice-ASR-Streaming Technical Report (arXiv:2609.02812v2), Table 3 single-speaker recognitionDutch ASR Leaderboard (tvosch) · committed result files+1
97Parakeet primeline (German) primeLine53±4*local~0.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
98Omnilingual ASR CTC 7B v2 Meta52±3*local~16GBhow to run › Open ASR Leaderboard
99Omnilingual ASR LLM 300M Meta52±2local~4.4GBhow to run › Open ASR LeaderboardOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)Open Universal Arabic ASR Leaderboard (Elm Research Center)Quranic ASR Leaderboard (Quran-Lab, held-out recitation set)
100Rev AI Machine (Reverb ASR) Rev52±3api $0.0033/audio mindocs.rev.ai ↗Open ASR Leaderboardverliapp/stt-benchmark · independent STT accuracy benchmark
101LiteWhisper large-v3-fast Efficient-Speech (LiteASR)52±3local~3.6GBhow to run › LiteASR (arXiv:2502.20583v2) · ESB WER of Whisper and LiteASR-compressed encodersOpen ASR Leaderboard
102VibeVoice-ASR-HF Microsoft52±3local~21GBhow to run › microsoft/VibeVoice-ASR-BitNet model card (Accuracy table)Open ASR Leaderboard
103OWSM-CTC v4 1B ESPnet (CMU WAVLab)52±4local~5.4GBhow to run › Open ASR LeaderboardOWSM v4 technical report (ESPnet / CMU WAVLab, arXiv:2506.00338v1): own OWSM-CTC scores
104Omnilingual ASR CTC 1B Meta51±2local~2.9GBhow to run › Open ASR LeaderboardOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)Open Universal Arabic ASR Leaderboard (Elm Research Center)
105Whisper large-v2 OpenAI51±2local~4.2GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardPESTE · Persian Speech to Text benchmark (fleurs-fa-ir-v1)German dialect ASR Benchmark (Betthupferl; kamaal-08/bavarian-asr-leaderboard)Open Universal Arabic ASR Leaderboard (Elm Research Center)Turkish ASR Leaderboard (TurkASR-Bench, yagmurtuncer)+1
106STT En Conformer-CTC Large NVIDIA51±4*local~1.1GBhow to run › Open ASR Leaderboard
107Omnilingual ASR LLM 300M v2 Meta51±3*local~4.4GBhow to run › Open ASR Leaderboard
108Moonshine Streaming Medium Useful Sensors (Moonshine AI)50±3local~1.8GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardPicovoice speech-to-text-benchmark · English batch-engine WER (README)
109VibeVoice-ASR-BitNet Microsoft50±4†local~1.7GBhow to run › microsoft/VibeVoice-ASR-BitNet model card (Accuracy table)
110Chirp Google50±4*comparison onlyOpen ASR Leaderboard
111Parakeet TDT-CTC 110M NVIDIA50±3local~1.1GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR Leaderboard
112ESPnet HuBERT Large + Conformer + Transformer LM ESPnet50±4*†local~8GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
113ESPnet WavLM Large + Conformer + Transformer LM ESPnet50±4*†local~8GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
114OWSM-CTC v3.1 1B ESPnet (CMU WAVLab)50±4local~5.4GBhow to run › Open ASR LeaderboardOWSM v4 technical report (ESPnet / CMU WAVLab, arXiv:2506.00338v1): own OWSM-CTC scores
115Multitalker Parakeet Streaming 0.6B v1 NVIDIA50±4*local~0.9GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
116Omnilingual ASR CTC 1B v2 Meta50±3local~2.9GBhow to run › Open ASR LeaderboardGerman dialect ASR Benchmark (Betthupferl; kamaal-08/bavarian-asr-leaderboard)Benchmarking Automatic Speech Recognition Tools for Iberian Languages (arXiv:2609.36920v1), Table 3
117Whisper large (v1) OpenAI49±2local~4.2GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardOpen Universal Arabic ASR Leaderboard (Elm Research Center)AfriSpeech-200 (arXiv:2310.00274v1) · zero-shot WER of open ASR models on African-accented English
118OWSM-CTC v3.2 ft 1B ESPnet (CMU WAVLab)49±4local~5.4GBhow to run › Open ASR LeaderboardOWSM v4 technical report (ESPnet / CMU WAVLab, arXiv:2506.00338v1): own OWSM-CTC scores
119Nemotron Speech Streaming EN 0.6B NVIDIA49±4*local~0.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
120Ultravox v0.6 (Llama 3.1 8B) Fixie.ai (Ultravox)49±5*comparison onlyOpen ASR Leaderboard
121Whisper medium.en OpenAI48±3local~2.4GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardPicovoice speech-to-text-benchmark · English batch-engine WER (README)AfriSpeech-200 (arXiv:2310.00274v1) · zero-shot WER of open ASR models on African-accented EnglishSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
122Distil-Whisper distil-large-v2 Hugging Face (Distil-Whisper)48±2local~2.3GBhow to run › distil-whisper/distil-large-v3.5 model cardOpen ASR Leaderboardhuggingface/distil-whisper README (Distil-Whisper headline WER table)
123Distil-Whisper distil-small.en Hugging Face (Distil-Whisper)48±4*local~0.9GBhow to run › Open ASR Leaderboardhuggingface/distil-whisper README (Distil-Whisper headline WER table)
124CrisperWhisper Nyra Health47±3local~4.4GBhow to run › AfriSpeech-MultiBench (arXiv:2511.14255v1) · African-accented English ASR benchmark suiteOpen ASR Leaderboard
125VibeVoice-ASR-Streaming-7B Microsoft47±5†local~17GBhow to run › VibeVoice-ASR-Streaming Technical Report (arXiv:2609.02812v2), Table 3 single-speaker recognition
126SpeechBrain Conformer (LargeScaleASR / Loquacious) SpeechBrain47±5*local~2.8GBhow to run › Open ASR LeaderboardSpeechBrain Hugging Face ASR model cards: published LibriSpeech/VoxPopuli WER for its own checkpoints
127GigaAM Multilingual Large (CTC 600M) Sber47±7*†local~2.3GBhow to run › ai-sage/GigaAM-Multilingual model card (Model Performance table)
128STT En Conformer-Transducer Large NVIDIA46±4local~1.1GBhow to run › Open ASR LeaderboardNVIDIA NeMo docs: ASR scores tables (English Conformer / FastConformer)
129ESPnet E-Branchformer (no LM) ESPnet46±4*†local~0.8GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
130ESPnet Multiconvformer (no LM) ESPnet46±4*†local~0.8GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
131STT En FastConformer-Transducer Large NVIDIA46±3local~1.1GBhow to run › Open ASR LeaderboardNVIDIA NeMo docs: ASR scores tables (English Conformer / FastConformer)
132Moonshine Streaming Small Useful Sensors (Moonshine AI)46±3local~1.2GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardPicovoice speech-to-text-benchmark · English batch-engine WER (README)
133SenseVoice Small Alibaba (FunAudioLLM)46±3local~0.3GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsmicrosoft/VibeVoice-ASR-BitNet model card (Accuracy table)
134STT En FastConformer-CTC Large NVIDIA45±3local~1.1GBhow to run › Open ASR LeaderboardNVIDIA NeMo docs: ASR scores tables (English Conformer / FastConformer)
135ESPnet wav2vec 2.0 Large + Conformer + Transformer LM ESPnet45±4*†local~8GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
136ESPnet Conformer + S4 decoder (no LM) ESPnet45±4*†local~8GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
137Omnilingual ASR CTC 300M Meta45±2local~1.3GBhow to run › Open ASR LeaderboardOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)Open Universal Arabic ASR Leaderboard (Elm Research Center)
138Distil-Whisper distil-medium.en Hugging Face (Distil-Whisper)44±3local~1.4GBhow to run › Open ASR Leaderboardhuggingface/distil-whisper README (Distil-Whisper headline WER table)
139Whisper small.en OpenAI44±3local~1.1GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardPicovoice speech-to-text-benchmark · English batch-engine WER (README)AfriSpeech-200 (arXiv:2310.00274v1) · zero-shot WER of open ASR models on African-accented EnglishSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
140ESPnet Branchformer 18-layer (70 epochs, no LM) ESPnet44±4*†local~0.7GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
141Nemotron 3.5 ASR Streaming 0.6B NVIDIA44±3local~0.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsVibeVoice-ASR-Streaming Technical Report (arXiv:2609.02812v2), Table 3 single-speaker recognitionPicovoice speech-to-text-benchmark · English batch-engine WER (README)Danish Speech-to-Text Leaderboard (RyeAI) · results datasetOpen Universal Arabic ASR Leaderboard (Elm Research Center)
142Whisper medium OpenAI43±2local~2.3GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsESPnet LibriSpeech ASR recipe results (pinned September 2026)Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)LiteASR (arXiv:2502.20583v2) · ESB WER of Whisper and LiteASR-compressed encodersPESTE · Persian Speech to Text benchmark (fleurs-fa-ir-v1)German dialect ASR Benchmark (Betthupferl; kamaal-08/bavarian-asr-leaderboard)+4
143Omnilingual ASR CTC 300M v2 Meta43±3*local~1.3GBhow to run › Open ASR Leaderboard
144STT En Conformer-Transducer Small NVIDIA43±3local~0.6GBhow to run › Open ASR LeaderboardNVIDIA NeMo docs: ASR scores tables (English Conformer / FastConformer)
145ESPnet Conformer 2020 + RNN LM ESPnet43±4*†local~1GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
146Vosk en-us 0.22 Alpha Cephei (Vosk)42±6local~16GBhow to run › Picovoice speech-to-text-benchmark · English batch-engine WER (README)Alpha Cephei Vosk models page (vendor-reported WER for its own Vosk models)
147GigaAM Multilingual (CTC 220M) Sber42±7*†local~0.9GBhow to run › ai-sage/GigaAM-Multilingual model card (Model Performance table)
148ESPnet Transformer 18-layer + RNN LM ESPnet42±4*†local~1GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
149ABR asr-19m-v2-en Applied Brain Research41±5*local~0.1GBhow to run › Open ASR Leaderboard
150SpeechBrain Transformer + TransformerLM (LibriSpeech) SpeechBrain40±7*†comparison onlySpeechBrain Hugging Face ASR model cards: published LibriSpeech/VoxPopuli WER for its own checkpoints
151ESPnet Multi-blank Transducer 8421 ESPnet40±4*†local~8GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
152ESPnet Conformer RNN-T (no LM) ESPnet40±4*†local~8GBhow to run › ESPnet LibriSpeech ASR recipe results (pinned September 2026)
153STT En Conformer-CTC Small NVIDIA39±3local~0.6GBhow to run › Open ASR LeaderboardNVIDIA NeMo docs: ASR scores tables (English Conformer / FastConformer)
154Whisper small OpenAI39±2local~1.1GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOmnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages (arXiv:2511.09690v1)verliapp/stt-benchmark · independent STT accuracy benchmarkPESTE · Persian Speech to Text benchmark (fleurs-fa-ir-v1)Open ASR Leaderboard – Chilean Spanish (idsudd / Alonso Astroza)German dialect ASR Benchmark (Betthupferl; kamaal-08/bavarian-asr-leaderboard)+5
155Moonshine Base Useful Sensors (Moonshine AI)38±3local~0.8GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR Leaderboard
156Whisper base.en OpenAI35±3local~0.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardPicovoice speech-to-text-benchmark · English batch-engine WER (README)Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
157SpeechBrain wav2vec2 CTC (LibriSpeech) SpeechBrain35±4local~2GBhow to run › Open ASR LeaderboardSpeechBrain Hugging Face ASR model cards: published LibriSpeech/VoxPopuli WER for its own checkpoints
158Vosk small en-us 0.15 Alpha Cephei (Vosk)31±6local~0.3GBhow to run › Picovoice speech-to-text-benchmark · English batch-engine WER (README)Alpha Cephei Vosk models page (vendor-reported WER for its own Vosk models)
159Moonshine Tiny Useful Sensors (Moonshine AI)29±3local~0.6GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR Leaderboard
160Moonshine Streaming Tiny Useful Sensors (Moonshine AI)28±3local~0.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardPicovoice speech-to-text-benchmark · English batch-engine WER (README)
161Whisper tiny.en OpenAI27±3local~0.6GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsOpen ASR LeaderboardPicovoice speech-to-text-benchmark · English batch-engine WER (README)Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
162MMS-1B-all Meta25±3local~5.1GBhow to run › Open ASR LeaderboardGerman dialect ASR Benchmark (Betthupferl; kamaal-08/bavarian-asr-leaderboard)Danish Speech-to-Text Leaderboard (RyeAI) · results datasetOpen Universal Arabic ASR Leaderboard (Elm Research Center)Turkish ASR Leaderboard (TurkASR-Bench, yagmurtuncer)Quranic ASR Leaderboard (Quran-Lab, held-out recitation set)
163Whisper base OpenAI25±3local~0.7GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsPESTE · Persian Speech to Text benchmark (fleurs-fa-ir-v1)German dialect ASR Benchmark (Betthupferl; kamaal-08/bavarian-asr-leaderboard)Danish Speech-to-Text Leaderboard (RyeAI) · results datasetTurkish ASR Leaderboard (TurkASR-Bench, yagmurtuncer)Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
164wav2vec 2.0 Large 960h LV-60 self-training Meta16±3local~2GBhow to run › Meta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsOpen ASR LeaderboardAfriSpeech-200 (arXiv:2310.00274v1) · zero-shot WER of open ASR models on African-accented EnglishSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
165HuBERT X-Large (LibriSpeech 960h ft) Meta16±4local~5.1GBhow to run › Open ASR LeaderboardMeta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsAfriSpeech-200 (arXiv:2310.00274v1) · zero-shot WER of open ASR models on African-accented EnglishSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
166HuBERT Large (LibriSpeech 960h ft) Meta15±4local~2GBhow to run › Open ASR LeaderboardMeta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
167wav2vec 2.0 Large Robust (LibriSpeech 960h ft) Meta15±5local~2GBhow to run › Open ASR LeaderboardSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR modelsDysarthric ASR with clinical context on the Speech Accessibility Project (arXiv:2605.02782v2)
168Whisper tiny OpenAI14±3local~0.6GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision portsPESTE · Persian Speech to Text benchmark (fleurs-fa-ir-v1)German dialect ASR Benchmark (Betthupferl; kamaal-08/bavarian-asr-leaderboard)Danish Speech-to-Text Leaderboard (RyeAI) · results datasetTurkish ASR Leaderboard (TurkASR-Bench, yagmurtuncer)Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
169wav2vec 2.0 Conformer Rel-Pos Large 960h Meta14±4local~3.5GBhow to run › Meta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsOpen ASR Leaderboard
170wav2vec 2.0 Conformer RoPE Large 960h Meta13±4local~3.3GBhow to run › Meta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsOpen ASR Leaderboard
171data2vec Audio Large 960h Meta13±4local~2GBhow to run › Meta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsOpen ASR Leaderboard
172wav2vec 2.0 Large 960h Meta7±3local~2GBhow to run › Meta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsOpen ASR LeaderboardAfriSpeech-200 (arXiv:2310.00274v1) · zero-shot WER of open ASR models on African-accented EnglishSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR modelsDysarthric ASR with clinical context on the Speech Accessibility Project (arXiv:2605.02782v2)
173data2vec Audio Base 960h Meta4±4local~1GBhow to run › Meta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsOpen ASR Leaderboard
174wav2vec 2.0 Base 960h Meta2±3local~1GBhow to run › Meta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpointsOpen ASR LeaderboardSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
175MMS-1B-FL102 Meta-9±5local~5.1GBhow to run › Open ASR LeaderboardSpeech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models
176MedASR Google-14±4*local~0.1GBhow to run › transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports
—MAI-Transcribe-2 Microsoft AIno reviewed resultsapi $0.0017/audio minazure.microsoft.com ↗
—Solaria-3 Gladiano reviewed resultsapi $0.010/audio minwww.gladia.io ↗

Includes 14 comparison-only models with no verified API or download · hide them

178 of 180 catalogue models listed here · sources and licences

Models outside this leaderboard (2 models)

No current run option verified: Jasper 10x5 (NVIDIA DLE, A100 recipe) · QuartzNet 15x5 (NVIDIA DLE, 21.07 recipe)

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory