SAVRN Model Hub · Comparisons
mms-300m-1130-forced-aligner vs whisper-small
Mms-300m-1130-forced-aligner has 315M parameters and whisper-small has 242M parameters; mms-300m-1130-forced-aligner is released under Creative Commons Attribution-NonCommercial 4.0 and whisper-small under Apache License 2.0; at 16-bit, mms-300m-1130-forced-aligner 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).
| Field | mms-300m-1130-forced-aligner MahmoudAshraf/mms-300m-1130-forced-aligner | whisper-small openai/whisper-small |
|---|---|---|
| Publisher | Mahmoud Ashraf | 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 | cc-by-nc-4.0 | 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 | 49402e9577b1 | 973afd24965f |
| Downloads reported by the hub | 2.6M | 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.
whisper-small
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| 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 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 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, mms-300m-1130-forced-aligner or whisper-small?
mms-300m-1130-forced-aligner (315M parameters) is larger than whisper-small (242M parameters), by the parameter counts their publishers report.
Which is cheaper to run, mms-300m-1130-forced-aligner or whisper-small?
At 4-bit, mms-300m-1130-forced-aligner 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 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.
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.