AI SeedbankHelp preserve open and free AI for humanity's future

← All models

jonatasgrosman_wav2vec2-large-xlsr-53-russian

jonatasgrosman · View on Hugging Face ↗

Get this model

Download TorrentMagnet Link

Seeders: · Leechers:

Model card

The complete upstream card, rendered from this payload's README.md — the same hash-verified bytes the torrent distributes. Images and off-site links are removed; the original card on Hugging Face carries them.


language: ru license: apache-2.0 datasets:

  • common_voice
  • mozilla-foundation/common_voice_6_0 metrics:
  • wer
  • cer tags:
  • audio
  • automatic-speech-recognition
  • hf-asr-leaderboard
  • mozilla-foundation/common_voice_6_0
  • robust-speech-event
  • ru
  • speech
  • xlsr-fine-tuning-week model-index:
  • name: XLSR Wav2Vec2 Russian by Jonatas Grosman results:
    • task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice ru type: common_voice args: ru metrics:
      • name: Test WER type: wer value: 13.3
      • name: Test CER type: cer value: 2.88
      • name: Test WER (+LM) type: wer value: 9.57
      • name: Test CER (+LM) type: cer value: 2.24
    • task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Robust Speech Event - Dev Data type: speech-recognition-community-v2/dev_data args: ru metrics:
      • name: Dev WER type: wer value: 40.22
      • name: Dev CER type: cer value: 14.8
      • name: Dev WER (+LM) type: wer value: 33.61
      • name: Dev CER (+LM) type: cer value: 13.5

Fine-tuned XLSR-53 large model for speech recognition in Russian

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Russian using the train and validation splits of Common Voice 6.1 and CSS10. When using this model, make sure that your speech input is sampled at 16kHz.

This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :)

The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint

Usage

The model can be used directly (without a language model) as follows...

Using the HuggingSound library:

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-russian")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]

transcriptions = model.transcribe(audio_paths)

Writing your own inference script:

import torch
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

LANG_ID = "ru"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-russian"
SAMPLES = 5

test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")

processor = Wav2Vec2Processor.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, sampling_rate = librosa.load(batch["path"], sr=16_000)
    batch["speech"] = speech_array
    batch["sentence"] = batch["sentence"].upper()
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
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_ids = torch.argmax(logits, dim=-1)
predicted_sentences = processor.batch_decode(predicted_ids)

for i, predicted_sentence in enumerate(predicted_sentences):
    print("-" * 100)
    print("Reference:", test_dataset[i]["sentence"])
    print("Prediction:", predicted_sentence)
Reference Prediction
ОН РАБОТАТЬ, А ЕЕ НЕ УДЕРЖАТЬ НИКАК — БЕГАЕТ ЗА КЛЁШЕМ КАЖДОГО БУЛЬВАРНИКА. ОН РАБОТАТЬ А ЕЕ НЕ УДЕРЖАТ НИКАК БЕГАЕТ ЗА КЛЕШОМ КАЖДОГО БУЛЬБАРНИКА
ЕСЛИ НЕ БУДЕТ ВОЗРАЖЕНИЙ, Я БУДУ СЧИТАТЬ, ЧТО АССАМБЛЕЯ СОГЛАСНА С ЭТИМ ПРЕДЛОЖЕНИЕМ. ЕСЛИ НЕ БУДЕТ ВОЗРАЖЕНИЙ Я БУДУ СЧИТАТЬ ЧТО АССАМБЛЕЯ СОГЛАСНА С ЭТИМ ПРЕДЛОЖЕНИЕМ
ПАЛЕСТИНЦАМ НЕОБХОДИМО СНАЧАЛА УСТАНОВИТЬ МИР С ИЗРАИЛЕМ, А ЗАТЕМ ДОБИВАТЬСЯ ПРИЗНАНИЯ ГОСУДАРСТВЕННОСТИ. ПАЛЕСТИНЦАМ НЕОБХОДИМО СНАЧАЛА УСТАНОВИТЬ С НИ МИР ФЕЗРЕЛЕМ А ЗАТЕМ ДОБИВАТЬСЯ ПРИЗНАНИЯ ГОСУДАРСТВЕНСКИ
У МЕНЯ БЫЛО ТАКОЕ ЧУВСТВО, ЧТО ЧТО-ТО ТАКОЕ ОЧЕНЬ ВАЖНОЕ Я ПРИБАВЛЯЮ. У МЕНЯ БЫЛО ТАКОЕ ЧУВСТВО ЧТО ЧТО-ТО ТАКОЕ ОЧЕНЬ ВАЖНОЕ Я ПРЕДБАВЛЯЕТ
ТОЛЬКО ВРЯД ЛИ ПОЙМЕТ. ТОЛЬКО ВРЯД ЛИ ПОЙМЕТ
ВРОНСКИЙ, СЛУШАЯ ОДНИМ УХОМ, ПЕРЕВОДИЛ БИНОКЛЬ С БЕНУАРА НА БЕЛЬ-ЭТАЖ И ОГЛЯДЫВАЛ ЛОЖИ. ЗЛАЗКИ СЛУШАЮ ОТ ОДНИМ УХАМ ТЫ ВОТИ В ВИНОКОТ СПИЛА НА ПЕРЕТАЧ И ОКЛЯДЫВАЛ БОСУ
К СОЖАЛЕНИЮ, СИТУАЦИЯ ПРОДОЛЖАЕТ УХУДШАТЬСЯ. К СОЖАЛЕНИЮ СИТУАЦИИ ПРОДОЛЖАЕТ УХУЖАТЬСЯ
ВСЁ ЖАЛОВАНИЕ УХОДИЛО НА ДОМАШНИЕ РАСХОДЫ И НА УПЛАТУ МЕЛКИХ НЕПЕРЕВОДИВШИХСЯ ДОЛГОВ. ВСЕ ЖАЛОВАНИЕ УХОДИЛО НА ДОМАШНИЕ РАСХОДЫ И НА УПЛАТУ МЕЛКИХ НЕ ПЕРЕВОДИВШИХСЯ ДОЛГОВ
ТЕПЕРЬ ДЕЛО, КОНЕЧНО, ЗА ТЕМ, ЧТОБЫ ПРЕВРАТИТЬ СЛОВА В ДЕЛА. ТЕПЕРЬ ДЕЛАЮ КОНЕЧНО ЗАТЕМ ЧТОБЫ ПРЕВРАТИТЬ СЛОВА В ДЕЛА
ДЕВЯТЬ ЛЕВЕТЬ

Evaluation

  1. To evaluate on mozilla-foundation/common_voice_6_0 with split test
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-russian --dataset mozilla-foundation/common_voice_6_0 --config ru --split test
  1. To evaluate on speech-recognition-community-v2/dev_data
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-russian --dataset speech-recognition-community-v2/dev_data --config ru --split validation --chunk_length_s 5.0 --stride_length_s 1.0

Citation

If you want to cite this model you can use this:

@misc{grosman2021xlsr53-large-russian,
  title={Fine-tuned {XLSR}-53 large model for speech recognition in {R}ussian},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-russian}},
  year={2021}
}

Magnet link

Opens the swarm directly in your torrent client — no file download needed. Copy-paste works too:

magnet:?xt=urn:btih:e12b473344d38a61b6255749a171c4b4db5c9727&dn=jonatasgrosman_wav2vec2-large-xlsr-53-russian

Open magnet in torrent client · infohash e12b473344d38a61b6255749a171c4b4db5c9727

Files & hashes

PathSizesha1sha256
README.md6.8 KB (6,912 B)cc695c442a445365ce7a609254b2cbf9d2d99388eb1f91a52c05d71fcef8b50615f255f17ba5c6fcdb8c1207a2971e041c224fc9
alphabet.json263 B (263 B)d7fa5c01fe60f507dea61fa91d97dbb6eba4e1413cde6d3da15a0573fd80c8c730960acd712cbafef3d1e32809eee9dbf30520ce
config.json1.7 KB (1,782 B)4e6ea0c631be11c63e48c6cb3c7fb9c20525735a9f02bcac826a79be1bc20cff20fb2ed830f3538ec282c65050f9195d61499deb
eval.py6.1 KB (6,198 B)cac50014eeb12f18e47067f3d2af8d6804e7359e9873f495d1b1768853bde2bf9f2ebf280a3f5e765e2ab8f67b75421ea4aa525f
full_eval.sh1.3 KB (1,372 B)33097b1d3a348df2629918c9fdcc8030ebcd2cb01ad8317518e0e943fb5f900ffd2b72206d865658c9b0b935d881b8c36f2cb18a
language_model/attrs.json78 B (78 B)3c07595c2b465df3c14531dbc2d1c52bf11f166df5ffd02e1ceef6517476e72ebe7997ddef7e92d27cb5a23d6695d64c4317d6ad
language_model/lm.binary1.38 GB (1,486,935,543 B)72b75ad40722600f39f372926a853cc1e0795ca201a8fba99ad0d5157e060ea7bee83adb7bc7025606e6f98a783da1413b6edbaf
language_model/unigrams.txt31.3 MB (32,849,086 B)dab7559c3dbb30c43d5c027cad3dda3c079ea193e7c72ae916afa54951fe3bd6094c95e2895c1c7881a20e02ef640aa27cdb4874
log_mozilla-foundation_common_voice_6_0_ru_test_predictions.txt1.0 MB (1,054,272 B)40bf26cd3c71642e7adb98a5ef90b741b02a88775bd10e81f5541d6e784d768d81f8cc9443793e4391bb5d19bdde525d7c4257af
log_mozilla-foundation_common_voice_6_0_ru_test_predictions_greedy.txt1.0 MB (1,054,819 B)20f68ff53fcd1afa5fde5cdf87a3b441b8ca1c1f87e25a8ed8fa04af413d81a6b23d0da7c47632c9e9180fe04cc0a2c60bbe5dc1
log_mozilla-foundation_common_voice_6_0_ru_test_targets.txt1.0 MB (1,057,641 B)66f38e56e22adc68643f00f049558baaa124613184095fdda745e72b5a6997c65a720f794d7ee5e8518f625e2620c7a6332485e5
log_speech-recognition-community-v2_dev_data_ru_validation_predictions.txt206.9 KB (211,890 B)99cd78b2d6537c3e7466a893885a396e101133122a4ff4b0085ac6b038f1db2b07e5837f21a8161b6022e244a72e8b76a91c220c
log_speech-recognition-community-v2_dev_data_ru_validation_predictions_greedy.txt207.3 KB (212,316 B)7ff45eb42bce419c33d72da77b11eae5ad62ff802b8c68580733c27506f3fabb3b116aca2e0ed05459ad149983025395605a57d4
log_speech-recognition-community-v2_dev_data_ru_validation_targets.txt201.2 KB (206,000 B)cc3f9ca2cf5fb999dc81e2047957a2891a8136282adcd40fbd916424668e0a9d91d43022a68566c1c4894a8f60cb82e0f621316e
mozilla-foundation_common_voice_6_0_ru_test_eval_results.txt50 B (50 B)2531ba62ee74720d61201553bc9bd27d4ceb33ae13c00b2498a96e293820536401d12cbca066369762537fbf52659cb0954ffef4
mozilla-foundation_common_voice_6_0_ru_test_eval_results_greedy.txt49 B (49 B)6df3d39b5e5d90de0e9299419cfac3fed22b977924b95eed95c2d3827f47effa96dcd47266f4277f9e0ae3523350b58db522ddfd
preprocessor_config.json262 B (262 B)bb3285bc209d674e3f88646bdfd327bfe43b60daca5999a45e98bb76ea87a461ba28a23ad32a5bb9f733b8e0f6546ff38b6c612d
pytorch_model.bin1.18 GB (1,262,093,719 B)8a296f93ed035b6d78a4bbc63ad2f659ce134ba7d1cdb1a7921de7d363f967a9b0101a713602e109dba62b6f3f9ae2e0b2df0c1c
special_tokens_map.json85 B (85 B)25bc39604f72700b3b8e10bd69bb2f227157edd1bb7068de1150661a10b55f9e4b12a0e77af8bf91f5e45e1b58afaf1d0e17f675
speech-recognition-community-v2_dev_data_ru_validation_eval_results.txt48 B (48 B)8e71b31fd2e2b9980411d2b7bae84349d1f4a38182b10c9816f662e81c7bb8526638e692582d30be5bbaa2540c4036a2410f979e
speech-recognition-community-v2_dev_data_ru_validation_eval_results_greedy.txt48 B (48 B)227444de6052e3d75143a99cc68441374b68f63f37ca846ed82ea830535e075d06b34f95346882d0e29e0e226df21635fd5e0cca
vocab.json387 B (387 B)7605a21c3ef6a87c6bcf8a5e86fc0b27605b082e3def5e6b6c6fcbe9a674e58b8f7f9e608742414db0188ec50bb3ac565612f0d7

Cite this release

Canonical URL
https://aiseedbank.org/models/jonatasgrosman_wav2vec2-large-xlsr-53-russian/
Slug
jonatasgrosman_wav2vec2-large-xlsr-53-russian
Infohash
e12b473344d38a61b6255749a171c4b4db5c9727
License
apache-2.0
Signing key fingerprint
85a3b32c3712427b

Every file carries a locally computed sha256 — verify a download against the signed sums: jonatasgrosman_wav2vec2-large-xlsr-53-russian.SHA256SUMS (+ minisign signature).

Provenance

Upstream repositoryjonatasgrosman/wav2vec2-large-xlsr-53-russian
Revision (pinned)2329100508896c6d9b157019803ab5601e6f3406
Fetched at2026-09-04T01:10:55Z
License at fetchapache-2.0
Snapshot toolhuggingface · seedbank 0.1.0

Trackers

✓ verified · rehash-vs-hf-metadata at 2026-09-04T01:11:30Z

apache-2.02.59 GB (2,785,692,820 bytes)transformerspytorchjaxwav2vec2automatic-speech-recognitionaudiohf-asr-leaderboardmozilla-foundation/common_voice_6_0robust-speech-eventspeechxlsr-fine-tuning-weekmodel-indexendpoints_compatible1 language (ru)