jonatasgrosman_wav2vec2-large-xlsr-53-russian
jonatasgrosman · View on Hugging Face ↗
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
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice ru
type: common_voice
args: ru
metrics:
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
- To evaluate on
mozilla-foundation/common_voice_6_0with splittest
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-russian --dataset mozilla-foundation/common_voice_6_0 --config ru --split test
- 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-russianOpen magnet in torrent client · infohash e12b473344d38a61b6255749a171c4b4db5c9727
Files & hashes
| Path | Size | sha1 | sha256 |
|---|---|---|---|
| README.md | 6.8 KB (6,912 B) | cc695c442a445365ce7a609254b2cbf9d2d99388 | eb1f91a52c05d71fcef8b50615f255f17ba5c6fcdb8c1207a2971e041c224fc9 |
| alphabet.json | 263 B (263 B) | d7fa5c01fe60f507dea61fa91d97dbb6eba4e141 | 3cde6d3da15a0573fd80c8c730960acd712cbafef3d1e32809eee9dbf30520ce |
| config.json | 1.7 KB (1,782 B) | 4e6ea0c631be11c63e48c6cb3c7fb9c20525735a | 9f02bcac826a79be1bc20cff20fb2ed830f3538ec282c65050f9195d61499deb |
| eval.py | 6.1 KB (6,198 B) | cac50014eeb12f18e47067f3d2af8d6804e7359e | 9873f495d1b1768853bde2bf9f2ebf280a3f5e765e2ab8f67b75421ea4aa525f |
| full_eval.sh | 1.3 KB (1,372 B) | 33097b1d3a348df2629918c9fdcc8030ebcd2cb0 | 1ad8317518e0e943fb5f900ffd2b72206d865658c9b0b935d881b8c36f2cb18a |
| language_model/attrs.json | 78 B (78 B) | 3c07595c2b465df3c14531dbc2d1c52bf11f166d | f5ffd02e1ceef6517476e72ebe7997ddef7e92d27cb5a23d6695d64c4317d6ad |
| language_model/lm.binary | 1.38 GB (1,486,935,543 B) | 72b75ad40722600f39f372926a853cc1e0795ca2 | 01a8fba99ad0d5157e060ea7bee83adb7bc7025606e6f98a783da1413b6edbaf |
| language_model/unigrams.txt | 31.3 MB (32,849,086 B) | dab7559c3dbb30c43d5c027cad3dda3c079ea193 | e7c72ae916afa54951fe3bd6094c95e2895c1c7881a20e02ef640aa27cdb4874 |
| log_mozilla-foundation_common_voice_6_0_ru_test_predictions.txt | 1.0 MB (1,054,272 B) | 40bf26cd3c71642e7adb98a5ef90b741b02a8877 | 5bd10e81f5541d6e784d768d81f8cc9443793e4391bb5d19bdde525d7c4257af |
| log_mozilla-foundation_common_voice_6_0_ru_test_predictions_greedy.txt | 1.0 MB (1,054,819 B) | 20f68ff53fcd1afa5fde5cdf87a3b441b8ca1c1f | 87e25a8ed8fa04af413d81a6b23d0da7c47632c9e9180fe04cc0a2c60bbe5dc1 |
| log_mozilla-foundation_common_voice_6_0_ru_test_targets.txt | 1.0 MB (1,057,641 B) | 66f38e56e22adc68643f00f049558baaa1246131 | 84095fdda745e72b5a6997c65a720f794d7ee5e8518f625e2620c7a6332485e5 |
| log_speech-recognition-community-v2_dev_data_ru_validation_predictions.txt | 206.9 KB (211,890 B) | 99cd78b2d6537c3e7466a893885a396e10113312 | 2a4ff4b0085ac6b038f1db2b07e5837f21a8161b6022e244a72e8b76a91c220c |
| log_speech-recognition-community-v2_dev_data_ru_validation_predictions_greedy.txt | 207.3 KB (212,316 B) | 7ff45eb42bce419c33d72da77b11eae5ad62ff80 | 2b8c68580733c27506f3fabb3b116aca2e0ed05459ad149983025395605a57d4 |
| log_speech-recognition-community-v2_dev_data_ru_validation_targets.txt | 201.2 KB (206,000 B) | cc3f9ca2cf5fb999dc81e2047957a2891a813628 | 2adcd40fbd916424668e0a9d91d43022a68566c1c4894a8f60cb82e0f621316e |
| mozilla-foundation_common_voice_6_0_ru_test_eval_results.txt | 50 B (50 B) | 2531ba62ee74720d61201553bc9bd27d4ceb33ae | 13c00b2498a96e293820536401d12cbca066369762537fbf52659cb0954ffef4 |
| mozilla-foundation_common_voice_6_0_ru_test_eval_results_greedy.txt | 49 B (49 B) | 6df3d39b5e5d90de0e9299419cfac3fed22b9779 | 24b95eed95c2d3827f47effa96dcd47266f4277f9e0ae3523350b58db522ddfd |
| preprocessor_config.json | 262 B (262 B) | bb3285bc209d674e3f88646bdfd327bfe43b60da | ca5999a45e98bb76ea87a461ba28a23ad32a5bb9f733b8e0f6546ff38b6c612d |
| pytorch_model.bin | 1.18 GB (1,262,093,719 B) | 8a296f93ed035b6d78a4bbc63ad2f659ce134ba7 | d1cdb1a7921de7d363f967a9b0101a713602e109dba62b6f3f9ae2e0b2df0c1c |
| special_tokens_map.json | 85 B (85 B) | 25bc39604f72700b3b8e10bd69bb2f227157edd1 | bb7068de1150661a10b55f9e4b12a0e77af8bf91f5e45e1b58afaf1d0e17f675 |
| speech-recognition-community-v2_dev_data_ru_validation_eval_results.txt | 48 B (48 B) | 8e71b31fd2e2b9980411d2b7bae84349d1f4a381 | 82b10c9816f662e81c7bb8526638e692582d30be5bbaa2540c4036a2410f979e |
| speech-recognition-community-v2_dev_data_ru_validation_eval_results_greedy.txt | 48 B (48 B) | 227444de6052e3d75143a99cc68441374b68f63f | 37ca846ed82ea830535e075d06b34f95346882d0e29e0e226df21635fd5e0cca |
| vocab.json | 387 B (387 B) | 7605a21c3ef6a87c6bcf8a5e86fc0b27605b082e | 3def5e6b6c6fcbe9a674e58b8f7f9e608742414db0188ec50bb3ac565612f0d7 |
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 repository | jonatasgrosman/wav2vec2-large-xlsr-53-russian |
|---|---|
| Revision (pinned) | 2329100508896c6d9b157019803ab5601e6f3406 |
| Fetched at | 2026-09-04T01:10:55Z |
| License at fetch | apache-2.0 |
| Snapshot tool | huggingface · seedbank 0.1.0 |
Trackers
- udp://announce.aitorrent.org:6969/announce
- http://announce.aitorrent.org:7070/announce
- udp://announce2.aitorrent.org:6970/announce
- http://announce2.aitorrent.org:7071/announce
- udp://tracker.opentrackr.org:1337/announce
- udp://open.demonii.com:1337/announce
- udp://open.stealth.si:80/announce
- udp://exodus.desync.com:6969/announce
- udp://tracker.torrent.eu.org:451/announce
✓ 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)