Mongolisk tal-till-text-ledartavla

Jämför ordelfrekvens, hastighet och pris mellan tal-till-text-leverantörer för mongoliska. Varje siffra är mätt på verkligt mongoliskt ljud — inte marknadsföring.

Datasets used

Public speech corpora used for every provider run. Open a source URL for the upstream dataset card, license, and download.

Common Voice 24 (MN)›https://huggingface.co/datasets/btsee/common-voices-24-mn
Shunya Labs Mongolian Speech›https://huggingface.co/datasets/shunyalabs/mongolian-speech-dataset
Common Voice 20 (MN)›https://huggingface.co/datasets/warmestman/common-voice-20-mn-normalized
Modern Voice›Recorded first-party for this benchmark — audio not distributed, metrics only.

WER vs. hastighet

Varje punkt är en leverantör. Det bästa läget är nedre högra (lite fel, snabbt). Mätt på verkligt mongoliskt ljud.

Google STTDuudlaga FlowSpeechmaticsChimegeOpenAI WhisperGPT-4o TranscribeAzure SpeechGladiaGemma 4Whisper large-v3Whisper large-v3-turboWhisper large-v2 MNSeamlessM4T v2MMS-1B-allMoonshine MNwav2vec2 XLSR-53 MNWhisper turbo MNWhisper medium MNElevenLabs Scribe v1ElevenLabs Scribe v2Qwen3-ASR-FlashDolphin smallOmniASR CTC-1BOmniASR LLM-1BVibeVoice ASRWhisper large-v3 MN

Leverantörsjämförelse

Sortera valfri kolumn. Klicka Detaljer för per-provs-uppdelning, priser och metod för en leverantör.

Öppen källkod

Leverantör	WER ↑	CER	Noggrannhet	Hastighet	Latens	Pris / 1000 min
Speechmatics	14.4%	7.4%	85.6%	0.51×	13.8s	$8.5	Detaljer
Duudlaga FlowVår	14.6%	7.6%	85.4%	1.47×	5.2s	$19.4	Detaljer
Chimege	14.6%	6.6%	85.4%	1.51×	4.7s	$11.1	Detaljer
Google STT	16.9%	7.4%	83.1%	1.98×	3.7s	$16	Detaljer
Whisper large-v2 MN	20.7%	8.3%	79.3%	0.53×	13.5s	$0	Detaljer
Azure Speech	20.8%	9.7%	79.2%	0.39×	17.3s	$16.7	Detaljer
Whisper medium MNOverlap	22.5%	8.9%	77.5%	2.7×	2.7s	$0	Detaljer
SeamlessM4T v2	24%	11.1%	76%	0.39×	26.3s	$0	Detaljer
Whisper turbo MNOverlap	25.7%	9.2%	74.3%	2.43×	3.0s	$0	Detaljer
ElevenLabs Scribe v1	27.1%	10.8%	72.9%	2.14×	3.3s	$6.7	Detaljer
ElevenLabs Scribe v2	27.1%	10.6%	72.9%	1.51×	4.7s	$3.7	Detaljer
Gemma 4	30.2%	14.7%	69.8%	1×	7.3s	$0	Detaljer
OmniASR LLM-1B	33.8%	14.2%	66.2%	0.27×	26.6s	$0	Detaljer
Whisper large-v3 MNOverlap	39.4%	14.9%	60.6%	1.57×	4.5s	$0	Detaljer
MMS-1B-all	41.7%	12.3%	58.3%	19.2×	0.4s	$0	Detaljer
wav2vec2 XLSR-53 MNOverlap	45%	16.4%	55%	42.32×	0.2s	$0	Detaljer
Dolphin small	49.1%	19.2%	50.9%	1.73×	4.1s	$0	Detaljer
OmniASR CTC-1B	51.2%	15.5%	48.8%	0.6×	11.7s	$0	Detaljer
GPT-4o Transcribe	53%	27.6%	47%	2.11×	3.7s	$6	Detaljer
Moonshine MNOverlap	58.8%	45.2%	41.2%	8.44×	0.8s	$0	Detaljer
Whisper large-v3	89.5%	37.4%	10.5%	1.29×	6.0s	$0	Detaljer
Gladia	90.1%	38.9%	9.9%	0.75×	9.4s	$10.2	Detaljer
Whisper large-v3-turbo	99%	54.4%	1%	0.91×	8.7s	$0	Detaljer
Qwen3-ASR-Flash	103.7%	86.4%	-3.7%	2.19×	3.2s	$2.1	Detaljer
OpenAI Whisper	105.2%	63.7%	-5.2%	1.5×	4.5s	$6	Detaljer
VibeVoice ASR	107%	61%	-7%	0.53×	12.1s	$0	Detaljer
Gemini Flash	Benchmark kommer snart

Alla resultat är mätta på verkliga mongoliska dataset. Hastighet är × realtid (högre = snabbare). Lägre WER är bättre.

Overlap— Models with this badge were trained on data that overlaps the benchmark corpora (Mongolian Common Voice — 113 of 173 samples — or the public Shunya Labs corpus). Scores on overlapping corpora are inflated by memorization; judge these models by the per-dataset table on their details page, especially the corpora they were NOT trained on.

Duudlaga Voice Set

92 samples · 10.2 min · 28 systems

A second corpus recorded first-party for this benchmark, covering what the public Mongolian datasets barely contain: modern loanwords, English/Mongolian code-switching, numbers, dates, and commands. Every system is measured on the same 92 recordings.

Leverantör	WER	CER	Noggrannhet	Hastighet
1Duudlaga FlowVår	9.5%	5.3%	90.5%	1.27×
2Google STT	11.7%	5.5%	88.3%	2.28×
3Chimege	14.5%	6.8%	85.5%	1.48×
4Speechmatics	15.3%	7.6%	84.7%	0.5×
5Gemini 3.5 Flash	19.5%	11.4%	80.5%	0.06×
6SeamlessM4T v2Öppen källkod	22.9%	10.4%	77.1%	4.32×
7Whisper large-v2 MNÖppen källkod	23.2%	10.9%	76.8%	0.55×
8ElevenLabs Scribe v1	23.4%	9.3%	76.6%	2.09×
9ElevenLabs Scribe v2	24.6%	9.8%	75.4%	1.47×
10Azure Speech	26.1%	10.9%	73.9%	0.32×
11Gemma 4Öppen källkod	27.7%	13.2%	72.3%	1.04×
12OmniASR LLM-1BÖppen källkod	34.5%	14.5%	65.5%	0.27×
13Whisper medium MNÖppen källkodOverlap	35.1%	14.8%	64.9%	2.71×
14Whisper turbo MNÖppen källkodOverlap	37.6%	14.1%	62.4%	2.59×
15Whisper large-v3 MNÖppen källkodOverlap	41%	17.1%	59%	1.58×
16GPT-4o Transcribe	44.3%	23.7%	55.7%	2.62×
17MMS-1B-allÖppen källkod	45.3%	15.1%	54.7%	20.52×
18Dolphin smallÖppen källkod	46.1%	19%	53.9%	1.69×
19W2v-BERT 2.0 MNÖppen källkodOverlap	46.3%	18.2%	53.7%	28.12×
20OmniASR CTC-1BÖppen källkod	54.9%	18.9%	45.1%	0.59×
21wav2vec2 XLSR-53 MNÖppen källkodOverlap	56.3%	23.9%	43.7%	45.7×
22Whisper large-v3Öppen källkod	87.3%	36.6%	12.7%	1.55×
23Gladia	88.1%	39.9%	11.9%	0.74×
24Moonshine MNÖppen källkodOverlap	96.2%	75.7%	3.8%	8.36×
25Whisper large-v3-turboÖppen källkod	98.1%	57.1%	1.9%	1.19×
26Qwen3-ASR-Flash	103.6%	89.9%	-3.6%	2.07×
27OpenAI Whisper	104.6%	63.8%	-4.6%	1.32×
28VibeVoice ASRÖppen källkod	110.1%	64%	-10.1%	0.4×

Recorded first-party for this benchmark — audio not distributed, metrics only.