SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

wav2vec2-xls-r-300m-hebrew vs whisper-small

Wav2vec2-xls-r-300m-hebrew has 315M parameters and whisper-small has 242M parameters; at 16-bit, wav2vec2-xls-r-300m-hebrew needs about 0.8 GB (1x MI300X from $1.85 an hour) and whisper-small about 0.6 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field wav2vec2-xls-r-300m-hebrew
imvladikon/wav2vec2-xls-r-300m-hebrew
whisper-small
openai/whisper-small
Publisher Vladimir Gurevich OpenAI
Task Speech recognition Speech recognition
Modality Audio Audio
Parameters, as reported 315M parameters 242M parameters
Architecture Wav2Vec2ForCTC WhisperForConditionalGeneration
Library transformers transformers
Context length Not stated Not stated
Repository size 2.5 GB 3.9 GB
Artifact formats safetensors, pytorch safetensors, pytorch, jax, tf
License Not stated apache-2.0
Access Open weights, no gate Open weights, no gate
Memory at 16-bit (weights and margin) 0.8 GB 0.6 GB
Cheapest GPUs at 16-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Memory at 4-bit (weights and margin) 0.2 GB 0.1 GB
Cheapest GPUs at 4-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Revision viewed b2e683004903 973afd24965f
Downloads reported by the hub 1.3M 2.9M
Last observed 2026-09-18 2026-09-18

An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.

Other Reported Results

These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.

wav2vec2-xls-r-300m-hebrew

BenchmarkConditionsResultReported byRevisionDate
Custom Dataset Task Automatic Speech RecognitionMetric Test WERComparison conditions not established 23.18 imvladikon
Publisher reported
Evaluated revision not stated

whisper-small

BenchmarkConditionsResultReported byRevisionDate
Common Voice 11.0 Configuration hiTask Automatic Speech RecognitionMetric Test WERComparison conditions not established 87.3 openai
Publisher reported
Evaluated revision not stated
Common Voice 13.0 Configuration dvTask Automatic Speech RecognitionMetric WerComparison conditions not established 125.698 openai
Publisher reported
Evaluated revision not stated
LibriSpeech (clean) Configuration cleanTask Automatic Speech RecognitionMetric Test WERComparison conditions not established 3.43221 openai
Publisher reported
Evaluated revision not stated
LibriSpeech (other) Configuration otherTask Automatic Speech RecognitionMetric Test WERComparison conditions not established 7.6283 openai
Publisher reported
Evaluated revision not stated

SAVRN's Notes on wav2vec2-xls-r-300m-hebrew

A vocabulary of 32 tokens tells you this is not a language model. It is a CTC speech recognizer for Hebrew that Vladimir Gurevich fine-tuned from facebook/wav2vec2-xls-r-300m in two stages, the second on a large mixed set that included weakly labeled audio. At 315M parameters it runs in 0.8 GB at 16-bit, 0.4 GB at 8-bit and 0.2 GB at 4-bit; the cheapest slot is one MI300X with 192 GB at $1.85 an hour on demand, far more card than it needs.

The license field is empty. Open access covers fetching the weights, nothing more: there is no stated grant for commercial use, modification or redistribution, so a buyer needs written terms from the publisher and a read of the base model's terms. The one reported number is a 23.18 test word error rate on the publisher's own dataset, so measure it on your own Hebrew audio.

SAVRN's Notes on whisper-small

Six tenths of a gigabyte at 16-bit, 0.1 GB at 4-bit: memory is not the question with whisper-small, OpenAI's 242M-parameter model for speech recognition and speech translation. The cheapest Index listing, one MI300X with 192 GB at $1.85 an hour on-demand, would sit nearly idle, so we run a model this size beside other work or fan many audio streams across one card. Disk is the bigger figure: 16 files totaling 3.87 GB, stored in float32.

Apache 2.0 permits commercial use, modification and redistribution, provided the license and copyright notices and any NOTICE file stay attached and significant changes are stated, and contributors grant patent rights. Two checks before committing: the page lists no token context length, so plan capacity in concurrent audio streams, and the Index shows no per-token host price for this model, so $1.85 an hour is the only benchmark.

Questions

Which is larger, wav2vec2-xls-r-300m-hebrew or whisper-small?

wav2vec2-xls-r-300m-hebrew (315M parameters) is larger than whisper-small (242M parameters), by the parameter counts their publishers report.

Which is cheaper to run, wav2vec2-xls-r-300m-hebrew or whisper-small?

At 4-bit, wav2vec2-xls-r-300m-hebrew fits on 1x MI300X from $1.85 an hour and whisper-small on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use whisper-small commercially?

Yes. whisper-small is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Related Comparisons