منگولین speech-to-text لیڈر بورڈ

منگولین کے لیے speech-to-text فراہم کنندگان کے لفظ غلطی کی شرح، رفتار اور قیمت کا موازنہ کریں۔ ہر عدد حقیقی منگولین آڈیو پر ناپا گیا — مارکیٹنگ نہیں۔

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.

WR بمقابلہ رفتار

ہر نقطہ ایک فراہم کنندہ ہے۔ بہترین جگہ نیچے-دائیں (کم غلطی، تیز)۔ حقیقی منگولین آڈیو پر ناپا گیا۔

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

فراہم کنندگان کا موازنہ

کوئی بھی کالم ترتیب دیں۔ کسی فراہم کنندہ کی فی نمونہ تفصیل، قیمتیں اور طریقہ کار کے لیے تفصیلات پر کلک کریں۔

اوپن سورس

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

تمام نتائج حقیقی منگولین ڈیٹاسیٹس پر ناپے گئے۔ رفتار × ریئل ٹائم ہے (زیادہ = تیز)۔ کم WER بہتر ہے۔

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.

فراہم کنندہ	WER	CER	درستگی	رفتار
1Duudlaga Flowہمارا	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 v2اوپن سورس	22.9%	10.4%	77.1%	4.32×
7Whisper large-v2 MNاوپن سورس	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 4اوپن سورس	27.7%	13.2%	72.3%	1.04×
12OmniASR LLM-1Bاوپن سورس	34.5%	14.5%	65.5%	0.27×
13Whisper medium MNاوپن سورسOverlap	35.1%	14.8%	64.9%	2.71×
14Whisper turbo MNاوپن سورسOverlap	37.6%	14.1%	62.4%	2.59×
15Whisper large-v3 MNاوپن سورسOverlap	41%	17.1%	59%	1.58×
16GPT-4o Transcribe	44.3%	23.7%	55.7%	2.62×
17MMS-1B-allاوپن سورس	45.3%	15.1%	54.7%	20.52×
18Dolphin smallاوپن سورس	46.1%	19%	53.9%	1.69×
19W2v-BERT 2.0 MNاوپن سورسOverlap	46.3%	18.2%	53.7%	28.12×
20OmniASR CTC-1Bاوپن سورس	54.9%	18.9%	45.1%	0.59×
21wav2vec2 XLSR-53 MNاوپن سورسOverlap	56.3%	23.9%	43.7%	45.7×
22Whisper large-v3اوپن سورس	87.3%	36.6%	12.7%	1.55×
23Gladia	88.1%	39.9%	11.9%	0.74×
24Moonshine MNاوپن سورسOverlap	96.2%	75.7%	3.8%	8.36×
25Whisper large-v3-turboاوپن سورس	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 ASRاوپن سورس	110.1%	64%	-10.1%	0.4×

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