--- license: apache-2.0 base_model: DataoceanAI1/dolphi-cn-dialect-small pipeline_tag: automatic-speech-recognition library_name: openasr tags: - automatic-speech-recognition - speech-to-text - openasr - oasr - dolphin ---
# Dolphin CN-Dialect Small Β· OpenASR **Chinese multi-dialect speech recognition -- a WeNet E-Branchformer (CTC + attention) tuned for Sichuan and 22 regional dialects** [![License](https://img.shields.io/badge/license-Apache--2.0-2563eb.svg)](https://huggingface.co/DataoceanAI1/dolphi-cn-dialect-small/blob/main/README.md) [![Format](https://img.shields.io/badge/format-.oasr-7c3aed.svg)](https://github.com/QuintinShaw/openasr) [![Runtime](https://img.shields.io/badge/runtime-OpenASR-111827.svg)](https://openasr.org) [![Base model](https://img.shields.io/badge/base-dolphi--cn--dialect--small-f59e0b.svg)](https://huggingface.co/DataoceanAI1/dolphi-cn-dialect-small) Native speech-to-text in the **[OpenASR](https://github.com/QuintinShaw/openasr)** runtime β€” engineered for peak performance on CPU & GPU, **no Python at inference time**.
--- ## ✨ Highlights - πŸ€„ **22 Chinese dialects** β€” 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** β€” a reported ~38% relative gain on dialect recognition and ~16% lower CER versus the base Dolphin, without giving up standard Mandarin - 🧩 **Joint CTC + attention** β€” 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** β€” a compact `small.cn` checkpoint over a character vocabulary, purpose-built for zh audio including heavy accents and code-mixed speech - πŸ¦€ **Native in OpenASR** β€” `.oasr` packs run with no Python at inference, engineered for peak performance on CPU & GPU ## πŸš€ Quickstart ```bash # 1. Install the OpenASR CLI Β· https://openasr.org # 2. Pull a build (pick a quant β€” see the table below) openasr pull dolphin-cn-dialect-small:fp16 # 3. Transcribe openasr transcribe audio.wav --model dolphin-cn-dialect-small ``` All builds for this model: ```bash openasr pull dolphin-cn-dialect-small:fp16 openasr pull dolphin-cn-dialect-small:q8 openasr pull dolphin-cn-dialect-small:q4 ``` ## πŸ“¦ Available builds | Quant | File (`.oasr`) | Size | RAM peak | RTF Β· M1 CPU | RTF Β· M1 GPU | Ξ”CER vs fp16 | |:------|:---------------|-----:|---------:|-------------:|-------------:|-----------------:| | fp16 | `dolphin-cn-dialect-small-fp16.oasr` | 860 MB | 2.37 GB | 0.32Γ— | 0.26Γ— | 0.0% | | q8_0 | `dolphin-cn-dialect-small-q8_0.oasr` | 494 MB | 2.88 GB | 0.24Γ— | 0.12Γ— | 0.0% | | q4_k | `dolphin-cn-dialect-small-q4_k.oasr` | 298 MB | 2.65 GB | 0.26Γ— | 0.11Γ— | 4.5% | RTF = real-time factor on a 2.38s in-language Sichuan-dialect (川话) clip (**lower is faster**); RAM peak measured per pack in an isolated subprocess. Ξ”CER compares each quantized build's Sichuan-clip transcript to this model's fp16 Sichuan-clip transcript, so it measures quantization drift rather than absolute recognition accuracy. **fp16** is the recommended default β€” near-reference quality at a fraction of the footprint. ## 🧠 About Dolphin CN-Dialect Small 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 β€” a standout **Sichuan (川话)** capability alongside 22 Chinese dialects such as Wu, Cantonese, Minnan and Shanghainese β€” 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 β€” 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. ## βš™οΈ How these packs were made Converted from [DataoceanAI1/dolphi-cn-dialect-small](https://huggingface.co/DataoceanAI1/dolphi-cn-dialect-small) with the OpenASR importer: ```bash openasr model-pack import dolphin .oasr \ --package-id dolphin-cn-dialect-small --quantization {fp16,q8-0,q4-k} ``` The `.oasr` container is GGUF-backed; packs use zero-copy mmap weight binding and graph buffer reuse to keep peak memory low. ## βš–οΈ License These packs **inherit the upstream model's license: Apache-2.0** ([source](https://huggingface.co/DataoceanAI1/dolphi-cn-dialect-small/blob/main/README.md)). OpenASR packaging retains the upstream copyright and NOTICE; the only modifications are format conversion and quantization. ## πŸ™ Acknowledgements This pack is a redistribution of **Dolphin CN-Dialect Small**, created and open-sourced by **DataoceanAI** ([DataoceanAI1/dolphi-cn-dialect-small](https://huggingface.co/DataoceanAI1/dolphi-cn-dialect-small)). All credit for the original architecture, training, and weights belongs to the authors; the license is inherited from and identical to the upstream model (Apache-2.0). The model builds on the **Dolphin** multilingual ASR project and the **WeNet** E-Branchformer / joint CTC-attention recipe β€” thank you to the Dolphin and WeNet teams and to DataoceanAI for releasing their work openly. OpenASR only performs format conversion, quantization, runtime verification, and local-inference adaptation. ## πŸ”— Links - πŸ¦€ **OpenASR** β€” - 🌐 **Website** β€” - πŸ€— **Upstream model** β€” [DataoceanAI1/dolphi-cn-dialect-small](https://huggingface.co/DataoceanAI1/dolphi-cn-dialect-small)