SAVRN Model Hub · Comparisons
mms-300m-1130-forced-aligner vs wav2vec2-xls-r-300m-hebrew
Mms-300m-1130-forced-aligner has 315M parameters and wav2vec2-xls-r-300m-hebrew has 315M parameters; at 16-bit, mms-300m-1130-forced-aligner needs about 0.8 GB (1x MI300X from $1.85 an hour) and wav2vec2-xls-r-300m-hebrew about 0.8 GB (1x MI300X from $1.85 an hour).
| Field | mms-300m-1130-forced-aligner MahmoudAshraf/mms-300m-1130-forced-aligner | wav2vec2-xls-r-300m-hebrew imvladikon/wav2vec2-xls-r-300m-hebrew |
|---|---|---|
| Publisher | Mahmoud Ashraf | Vladimir Gurevich |
| Task | Speech recognition | Speech recognition |
| Modality | Audio | Audio |
| Parameters, as reported | 315M parameters | 315M parameters |
| Architecture | Wav2Vec2ForCTC | Wav2Vec2ForCTC |
| Library | transformers | transformers |
| Context length | Not stated | Not stated |
| Repository size | 2.5 GB | 2.5 GB |
| Artifact formats | safetensors, pytorch | safetensors, pytorch |
| License | cc-by-nc-4.0 | Not stated |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.8 GB | 0.8 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 | 0.2 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 49402e9577b1 | b2e683004903 |
| Downloads reported by the hub | 2.6M | 1.3M |
| 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
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| Custom Dataset | Task Automatic Speech RecognitionMetric Test WERComparison conditions not established | 23.18 | imvladikon Publisher reported |
Evaluated revision not stated | — |
SAVRN's Notes on mms-300m-1130-forced-aligner
For aligning a transcript to its audio, this Wav2Vec2ForCTC checkpoint runs in 0.8 GB of memory at 16-bit, 0.6 GB of it weights. Mahmoud Ashraf converted the MMS-300M forced-alignment weights from torchaudio to Transformers and ships a Python package that uses much less memory than the TorchAudio alignment API. At 315M parameters over 24 layers, it uses a sliver of the cheapest setup we list, one MI300X with 192 GB at $1.85 per hour on-demand, so schedule it beside other audio work.
The license is where deployment plans change. CC BY-NC 4.0 allows sharing and adapting with credit for non-commercial purposes only, and commercial use needs separate permission from the rights holder, so a paid product cannot ship on it without that permission. Stored precision is float32, so the 9 files come to 2.5 GB on disk. Vocabulary is 31 entries; last update April 15, 2026.
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.
Questions
Which is larger, mms-300m-1130-forced-aligner or wav2vec2-xls-r-300m-hebrew?
wav2vec2-xls-r-300m-hebrew (315M parameters) is larger than mms-300m-1130-forced-aligner (315M parameters), by the parameter counts their publishers report.
Which is cheaper to run, mms-300m-1130-forced-aligner or wav2vec2-xls-r-300m-hebrew?
At 4-bit, mms-300m-1130-forced-aligner fits on 1x MI300X from $1.85 an hour and wav2vec2-xls-r-300m-hebrew on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use mms-300m-1130-forced-aligner commercially?
Not without separate permission. mms-300m-1130-forced-aligner is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.