Dolphin CN-Dialect Small
Chinese multi-dialect speech recognition -- a WeNet E-Branchformer (CTC + attention) tuned for Sichuan and 22 regional dialects
Opens the desktop app and downloads this model for you.
Don't have the app yet? Download OpenASR Desktop
let's line up this week's release plan,
the beta build can ship on Friday,
then loop in design and QA,
Why it fits
Dolphin CN-Dialect Small is a Chinese multi-dialect speech-recognition model from
DataoceanAI, built on the Dolphin / WeNet recipe as an E-Branchformer encoder +
Transformer decoder trained with a joint CTC + attention objective (the small.cn
checkpoint over a character vocabulary). It specializes in regional Mandarin — a standout
Sichuan (川话) capability alongside 22 Chinese dialects such as Wu, Cantonese, Minnan and
Shanghainese — while keeping strong standard-Mandarin transcription (the card reports a large
relative gain on dialect recognition and a meaningful CER reduction over the base Dolphin).
This OpenASR repo repackages the weights as .oasr packs that run natively in the OpenASR
runtime — no Python at inference, all decoding local. OpenASR decodes it with CTC beam search
plus attention rescoring and verified the transcript bit-exact against a golden reference on a
Sichuan-dialect clip. It ships in fp16 (maximum fidelity, recommended), q8_0, and q4_k builds.
Note: this model does not emit punctuation. Its upstream training corpus is transcribed
without punctuation marks, so the decoder never predicts a punctuation token -- there is no
setting to enable it. Transcripts are plain, unpunctuated text by design.
What you can do with it
- 🀄 22 Chinese dialects — a WeNet E-Branchformer tuned for regional Mandarin, with a standout Sichuan (川话) strength across Wu, Cantonese, Minnan, Shanghainese and more
- 🎯 Dialect-first accuracy — a reported ~38% relative gain on dialect recognition and ~16% lower CER versus the base Dolphin, without giving up standard Mandarin
- 🧩 Joint CTC + attention — an E-Branchformer encoder with a Transformer decoder and CTC/attention rescoring that OpenASR runs bit-exact against its golden reference
- 🐬 Chinese-focused, char-level — a compact
small.cncheckpoint over a character vocabulary, purpose-built for zh audio including heavy accents and code-mixed speech - 🦀 Native in OpenASR —
.oasrpacks run with no Python at inference, engineered for peak performance on CPU & GPU
Other models
Developer details CLI commands, file hashes, and per-quant downloads — for scripting and verification.
Model facts
Usage
These are CLI / local-server examples. The desktop app runs this model without typing a command — use Install above.
$ openasr pull dolphin-cn-dialect-small:fp16 ↓ dolphin-cn-dialect-small.oasr 820.1 MB ✓ verified sha256 $ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/dolphin-cn-dialect-small/fp16/dolphin-cn-dialect-small-fp16.oasr ✓ local transcript · 0 bytes sent
$ openasr serve --backend native --model-pack ~/.openasr/models/dolphin-cn-dialect-small/fp16/dolphin-cn-dialect-small-fp16.oasr --addr 127.0.0.1:8080 ▶ http://127.0.0.1:8080 · model=dolphin-cn-dialect-small · 0 bytes will leave this host
from openai import OpenAI client = OpenAI(base_url="http://127.0.0.1:8080/v1", api_key="local") audio = open("meeting.wav", "rb") text = client.audio.transcriptions.create(model="dolphin-cn-dialect-small", file=audio)