Model reference · open weights

wav2vec2-large-xlsr-cantonese

Available as managed deployment Audio scottykwok · community Speech→text 1 variants 35k dl/mo

wav2vec2-large-xlsr-cantonese is an open-weight audio or speech model from scottykwok. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byscottykwok
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2022-03-02
Popularity35k downloads / month
LicenceOpen weights

About

What wav2vec2-large-xlsr-cantonese is

This model was based on wav2vec2-large-xlsr-53, finetuned using Common Voice/zh-HK/6.1.0.

The training code is similar to user ctl, except that the number of training epochs was 80 (doubled) and fp16_backend is apex. The model was trained using a single RTX 3090 and docker image is nvidia/cuda:11.1-cudnn8-devel.

CER is 15.11% when evaluate against common voice zh-HK test set.

Read the full model card

Result (CER)

15.11%

Source Code

See this GitHub Repo cantonese-selfish-project and demo video.

Usage

import soundfile as sf
import torch
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

# load pretrained model
processor = Wav2Vec2Processor.from_pretrained("scottykwok/wav2vec2-large-xlsr-cantonese")
model = Wav2Vec2ForCTC.from_pretrained("scottykwok/wav2vec2-large-xlsr-cantonese")

# load audio - must be 16kHz mono
audio_input, sample_rate = sf.read('audio.wav')

# pad input values and return pt tensor
input_values = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt").input_values

# INFERENCE
# retrieve logits & take argmax
logits = model(input_values).logits
predicted_ids = torch.argmax(logits, dim=-1)

# transcribe
transcription = processor.decode(predicted_ids[0])
print("-" *20)
print("Transcription:\n", transcription.lower())
print("-" *20)

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys wav2vec2-large-xlsr-cantonese for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-cantonese below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="wav2vec2-large-xlsr-cantonese" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms