Mongolian Speech-to-Text Leaderboard
Whisper large-v2 MNOperating point: bayartsogt/whisper-large-v2-mn-13 (Mongolian fine-tune) on mps

Whisper large-v2 MN — Mongolian Speech-to-Text Benchmark

Real results from the Whisper large-v2 MN Batch API (enhanced operating point, language mn) evaluated across 4 Mongolian datasets and 265 audio samples. Every number below is measured — not marketing. WER, speed, and pricing are shown as-is, brutally honest.

Language:MNDiarization:noneSamples:265Run:Aug 18, 2026, 4:09 PMEndpoint:local (transformers)
06710079.3%
Accuracy

265/265 samples transcribed · 100% success rate

06710020.7%
Word Error Rate

Lower is better · across 265 samples

Headline metrics
Character Error Rate8.3%
Avg speed factor0.53×realtime multiple
Total speed factor0.53×
Avg latency / sample13.5s
Total audio processed1849.3s30.8 min

Pricing

Whisper large-v2 MN list pricing for batch transcription. No discounts, no negotiated rates applied — the raw per-minute rate.

Per 1k minutes
$0
batch
Per minute
$0.0000
effective
Per 1k min (these 30.8 min)
$0.00
would cost
Open source?
proprietary

Pricing source: Whisper large-v2 MN public pricing. Duudlaga Flow is shown for context only — this page isolates Whisper large-v2 MN so the number is not padded by our own product.

WER & CER by dataset

Word and character error rates per dataset. Lower is better — and these are the real Whisper large-v2 MN numbers, which are weak on Common Voice 24.

Common Voice 24 (MN)
Source dataset →
WER
18.7%
CER
6%
Shunya Labs Mongolian Speech
Source dataset →
WER
16.7%
CER
6.1%
Common Voice 20 (MN)
Source dataset →
WER
16.7%
CER
5.1%
Modern Voice
WER
26.8%
CER
13.3%
WERCER

Dataset summary

Aggregate accuracy, speed, and timing for each dataset.

DatasetSourceSamplesSuccessWERCERAccuracySpeedAudio (s)Proc (s)
Common Voice 24 (MN)Hugging Face →5959/5918.7%6%81.3%0.57×330.6s575.3s
Shunya Labs Mongolian SpeechHugging Face →6060/6016.7%6.1%83.3%0.52×645.1s1241.4s
Common Voice 20 (MN)Hugging Face →5454/5416.7%5.1%83.3%0.51×269.8s526.3s
Modern Voice9292/9226.8%13.3%73.2%0.54×603.8s1114.9s

WER vs speed — per sample

Each dot is one audio sample. The sweet spot is the bottom-left (low error, fast). Whisper large-v2 MN sits high on error for many Common Voice 24 samples.

Per-sample results

Ground truth shown verbatim in the Expected column. The result column highlights only the words Whisper large-v2 MN got wrong, in red — no strikethrough/swap gymnastics, just the mistakes.

265 rows
redwrong word in the resultplaincorrectly transcribedExpected column shown verbatim as ground truth
#AudioSampleDatasetExpected (ground truth)Whisper large-v2 MN resultWERCERI/D/S
1btsee_0001Common Voice 24 (MN)Гэхдээ амьсгал хураахаасаа өмнө танд мэдэж байгаагаа хэлье.гэхдээ амьсгал хураахаасаа өмнө танд мэдэж байгаагаа хэлье.0.0%0.0%0/0/0
2btsee_0002Common Voice 24 (MN)Надад заяасан аз жаргал гэдэг ердөө гуравхан сарын хугацаатай байсан гэж үү?надад заяасан аз жаргал гэдэг ердөө гуравхан сарын хугацаатай байсан гэж үү.0.0%0.0%0/0/0
3btsee_0003Common Voice 24 (MN)Одоо бид өөрсдөө өвчин эмгэгээсээ салахыг хичээцгээе.одоо бид өөрсдөө өвчин эмгэгээсээ салахыг хичээцгээе.0.0%0.0%0/0/0
4btsee_0004Common Voice 24 (MN)Би бол голдуу хээрээр гэр, хэцээр дэр хийж явдаг хүн.би бол голдуу хээрээр гэр, хэцээр дэр хийж явдаг хүн.0.0%0.0%0/0/0
5btsee_0005Common Voice 24 (MN)Хан хурмаст уурлаж, Болдоггүй Бор өвгөнийг хор луугаараа ниргүүлэхээр явуулжээ.ханх оромжт уурлас болдоггүй баруун хүнийг хоёр луугаар нэргүйлэхээр явжээ.90.0%28.6%0/0/9
6btsee_0006Common Voice 24 (MN)Алив наашаа ороод ир гээд гэртээ оров.алив наашаа ороод ир гээд гэртээ оров.0.0%0.0%0/0/0
7btsee_0007Common Voice 24 (MN)Өө өндөр дээдэс таны тухайд би баталж чадахгүй.өө, өндөр дээдэс таны тухайд би баталж чадахгүй.0.0%0.0%0/0/0
8btsee_0008Common Voice 24 (MN)Харин гурав дахь удаагаас эхлэн хүмүүсийг сонирхож эхлэв.харин гурав дахь удаагаасаа эхлэх хүмүүсийг сонирхож эхлэв.25.0%5.4%0/0/2
9btsee_0009Common Voice 24 (MN)Та нар очингуутаа шөл л өгч үз.та нар очингуутаа шөл л өгч үз.0.0%0.0%0/0/0
10btsee_0010Common Voice 24 (MN)Ерөөсөө литр үйлдвэрээсээ салаагүй явсан юм чинь.ерөөсөө л үйлдвэрээсээ салаагүй явсан юм чинь.14.3%6.2%0/0/1
Page 1 of 27

Methodology

How these numbers were produced.

Provider: Whisper large-v2 MN (Whisper large-v2 fine-tuned on Mongolian Common Voice by the bayartsogt community project — the most-downloaded Mongolian-specific open ASR model.).

Endpoint local (transformers). Language mn. Operating point bayartsogt/whisper-large-v2-mn-13 (Mongolian fine-tune) on mps. Diarization none.

Datasets: Common Voice 24 (MN), Shunya Labs Mongolian Speech, Common Voice 20 (MN), Modern Voice — 265 samples, 1849.3s of audio total.

Dataset source URLs:

Metrics: WER and CER are computed with a standard word/character Levenshtein alignment, normalized for case and punctuation. Accuracy = 100 − WER. Speed factor = audio duration ÷ processing time (× realtime). All requests are real Whisper large-v2 MN Batch API calls, not cached or simulated.

Diff highlighting: The result column aligns to the ground truth and colors every substitution and insertion red. Deletions (words missing from the result) are not shown in the result column — the Expected column already holds the full ground truth as-is.

Generated by the Whisper large-v2 MN Benchmark Runner · Whisper large-v2 MN Batch API v2 · run Aug 18, 2026, 4:09 PM