Model reference · open weights

romanian-wav2vec2

romanian-wav2vec2 is an open-weight audio or speech model from gigant, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio gigant 1 variants 1.6M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What romanian-wav2vec2 is

You can test this model online with the Space for Romanian Speech Recognition The model ranked TOP-1 on Romanian Speech Recognition during HuggingFace's Robust Speech Challenge : The 🤗 Speech Bench Speech Challenge Leaderboard Romanian Wav2Vec2 This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice 8.0 - Romanian subset dataset, with extra training data from Romanian Speech Synthesis dataset. Without the 5-gram Language Model optimization, it achieves the following results on the evaluation set (Common Voice 8.0, Romanian subset, test split): - Loss: 0.1553 - Wer: 0.1174 - Cer: 0.0294 Model description The architecture is based on facebook/wav2vec2-xls-r-300m with a speech recognition CTC head and an added 5-gram language model (using pyctcdecode and kenlm) trained on the Romanian Corpora Parliament dataset. Those libraries are needed in order for the language model-boosted decoder to work. Intended uses & limitations The model is made for speech recognition in Romanian from audio clips sampled at 16kHz. The predicted text is lowercased and does not contain any punctuation. How to use Make sure you have installed the correct dependencies for the language model-boosted version to work. You can just run this command to install the kenlm and pyctcdecode libraries : from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.frompretrained("gigant/romanian-wav2vec2") model = AutoModelForCTC.frompretrained("gigant/romanian-wav2vec2") from transformers import pipeline asr = pipeline("automatic-speech-recognition", model="gigant/romanian-wav2vec2") from datasets import loaddataset dataset = loaddataset("gigant/romanianspeechsynthesis081") from IPython.display import Audio i = 0 sample = dataset["train"][i] Audio(sample["audio"]["array"], rate = sample["audio"]["samplingrate"]) import torchaudio import torch i = 0 audio = sample["audio"]["array"] rate = sample["audio"]["samplingrate"] resampler = torchaudio.transforms.Resample(rate, 16000) audio16 = resampler(torch.Tensor(audio)).numpy() Audio(audio16, rate=16000) predictedtext = asr(audio16) groundtruth = dataset["train"][i]["sentence"] print(f"Predicted text : {pre

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makergigant
TypeAudio & music
Parameters (lead)315M
Variants1
Runs withtransformers
Based onfacebook/wav2vec2-xls-r-300m
Released2022-03-02
Popularity1.6M downloads / month
Likes8
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
romanian-wav2vec2315MBF16~0.7 GBWeights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Automatic Speech RecognitionRobust Speech EventDev WER (without LM)46.99
Automatic Speech RecognitionRobust Speech EventDev CER (without LM)16.04
Automatic Speech RecognitionRobust Speech EventDev WER (with LM)38.63
Automatic Speech RecognitionRobust Speech EventDev CER (with LM)14.52
Automatic Speech RecognitionCommon VoiceTest WER (without LM)11.73
Automatic Speech RecognitionCommon VoiceTest CER (without LM)2.93
Automatic Speech RecognitionCommon VoiceTest WER (with LM)7.31
Automatic Speech RecognitionCommon VoiceTest CER (with LM)2.17
Automatic Speech RecognitionRobust Speech Event - Test DataTest WER43.23

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys romanian-wav2vec2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (romanian-wav2vec2 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="romanian-wav2vec2" -F file=@audio.mp3

Details

Languages, data & research

Languages

ro

Trained / evaluated on

mozilla-foundation/common_voice_8_0 gigant/romanian_speech_synthesis_0_8_1

Tags

transformers pytorch safetensors wav2vec2 automatic-speech-recognition hf-asr-leaderboard robust-speech-event ro dataset:mozilla-foundation/common_voice_8_0 dataset:gigant/romanian_speech_synthesis_0_8_1 model-index endpoints_compatible

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want romanian-wav2vec2 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

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