Model reference · open weights

wav2vec2-large-ru-golos-with-lm

Available as managed deployment Audio bond005 · community Speech→text 1 variants 11k dl/mo

wav2vec2-large-ru-golos-with-lm is an open-weight audio or speech model from bond005. 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 bybond005
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2022-09-26
Popularity11k downloads / month
LicenceOpen weights

About

What wav2vec2-large-ru-golos-with-lm is

The Wav2Vec2 model is based on facebook/wav2vec2-large-xlsr-53, fine-tuned in Russian using Sberdevices Golos with audio augmentations like as pitch shift, acceleration/deceleration of sound, reverberation etc.

The 2-gram language model is built on the Russian text corpus obtained from three open sources:

Read the full model card

Usage

When using this model, make sure that your speech input is sampled at 16kHz.

You can use this model by writing your own inference script:

import os
import warnings

import librosa
import nltk
import numpy as np

import torch
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2ProcessorWithLM

MODEL_ID = "bond005/wav2vec2-large-ru-golos-with-lm"
DATASET_ID = "bond005/sberdevices_golos_10h_crowd"
SAMPLES = 30

nltk.download('punkt')
num_processes = max(1, os.cpu_count())

test_dataset = load_dataset(DATASET_ID, split=f"test[:{SAMPLES}]")
processor = Wav2Vec2ProcessorWithLM.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)

# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
    speech_array = batch["audio"]["array"]
    batch["speech"] = np.asarray(speech_array, dtype=np.float32)
    return batch

removed_columns = set(test_dataset.column_names)
removed_columns -= {'transcription', 'speech'}
removed_columns = sorted(list(removed_columns))
with warnings.catch_warnings():
    warnings.simplefilter("ignore")
    test_dataset = test_dataset.map(
        speech_file_to_array_fn,
        num_proc=num_processes,
        remove_columns=removed_columns
    )

inputs = processor(test_dataset["speech"], sampling_rate=16_000,
                   return_tensors="pt", padding=True)
with torch.no_grad():
    logits = model(inputs.input_values,
                   attention_mask=inputs.attention_mask).logits
predicted_sentences = processor.batch_decode(
    logits=logits.numpy(),
    num_processes=num_processes
).text

with warnings.catch_warnings():
    warnings.simplefilter("ignore")
    for i, predicted_sentence in enumerate(predicted_sentences):
        print("-" * 100)
        print("Reference:", test_dataset[i]["transcription"])
        print("Prediction:", predicted_sentence)
----------------------------------------------------------------------------------------------------
Reference:   шестьдесят тысяч тенге сколько будет стоить
Prediction:  шестьдесят тысяч тенге сколько будет стоить
----------------------------------------------------------------------------------------------------
Reference:   покажи мне на смотрешке телеканал синергия тв
Prediction:  покажи мне на смотрешке телеканал синергия тв
----------------------------------------------------------------------------------------------------
Reference:   заказать яблоки зеленые
Prediction:  заказать яблоки зеленые
----------------------------------------------------------------------------------------------------
Reference:   алиса закажи килограммовый торт графские развалины
Prediction:  алиса закажи килограммовый торт графские развалины
----------------------------------------------------------------------------------------------------
Reference:   ищи телеканал про бизнес на тиви
Prediction:  ищи телеканал про бизнес на тиви
----------------------------------------------------------------------------------------------------
Reference:   михаила мурадяна
Prediction:  михаила мурадяна
----------------------------------------------------------------------------------------------------
Reference:   любовницы две тысячи тринадцать пятнадцатый сезон
Prediction:  любовница две тысячи тринадцать пятнадцатый сезон
----------------------------------------------------------------------------------------------------
Reference:   найди боевики
Prediction:  найди боевики
----------------------------------------------------------------------------------------------------
Reference:   гетто сезон три
Prediction:  гета сезон три
----------------------------------------------------------------------------------------------------
Reference:   хочу посмотреть ростов папа на телевизоре
Prediction:  хочу посмотреть ростоу папа на телевизоре
----------------------------------------------------------------------------------------------------
Reference:   сбер какое твое самое ненавистное занятие
Prediction:  сбер какое твое самое ненавистное занятие
----------------------------------------------------------------------------------------------------
Reference:   афина чем платят у китайцев
Prediction:  афина чем платят у китайцев
----------------------------------------------------------------------------------------------------
Reference:   джой как работает досрочное погашение кредита
Prediction:  джой как работает досрочное погашение кредита
----------------------------------------------------------------------------------------------------
Reference:   у тебя найдется люк кейдж
Prediction:  у тебя найдется люк кейдж
----------------------------------------------------------------------------------------------------
Reference:   у тебя будет лучшая часть пинк
Prediction:  у тебя будет лучшая часть пинк
----------------------------------------------------------------------------------------------------
Reference:   пожалуйста пополните мне счет
Prediction:  пожалуйста пополните мне счет
----------------------------------------------------------------------------------------------------
Reference:   анне павловне шабуровой
Prediction:  анне павловне шабуровой
----------------------------------------------------------------------------------------------------
Reference:   врубай на смотрешке муз тв
Prediction:  врубай на смотрешке муз 

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

Benchmarks

Reported results

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

TaskDatasetMetricScore
Speech RecognitionSberdevices Golos (crowd)Test WER6.883
Speech RecognitionSberdevices Golos (crowd)Test CER1.637
Speech RecognitionSberdevices Golos (farfield)Test WER15.044
Speech RecognitionSberdevices Golos (farfield)Test CER5.128
Automatic Speech RecognitionCommon Voice ruTest WER12.115
Automatic Speech RecognitionCommon Voice ruTest CER2.980
Automatic Speech RecognitionRussian LibrispeechTest WER15.736
Automatic Speech RecognitionRussian LibrispeechTest CER3.573
Automatic Speech RecognitionSova RuDevicesTest WER20.652
Automatic Speech RecognitionSova RuDevicesTest CER7.287
Automatic Speech RecognitionVoxforge RuTest WER19.079
Automatic Speech RecognitionVoxforge RuTest CER5.864

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys wav2vec2-large-ru-golos-with-lm for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-ru-golos-with-lm 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-ru-golos-with-lm" -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