SAVRN Model Hub · Comparisons
wav2vec2-xls-r-300m-ftspeech vs whisper-small
Wav2vec2-xls-r-300m-ftspeech has 315M parameters and whisper-small has 242M parameters; wav2vec2-xls-r-300m-ftspeech is released under other and whisper-small under Apache License 2.0; at 16-bit, wav2vec2-xls-r-300m-ftspeech 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 | wav2vec2-xls-r-300m-ftspeech saattrupdan/wav2vec2-xls-r-300m-ftspeech | whisper-small openai/whisper-small |
|---|---|---|
| Publisher | Dan Saattrup Smart | 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 | 3.8 GB | 3.9 GB |
| Artifact formats | safetensors, pytorch | safetensors, pytorch, jax, tf |
| License | other | 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 | 7a60985d596e | 973afd24965f |
| Downloads reported by the hub | 829.9k | 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-ftspeech
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| Alvenir ASR test dataset | Task automatic-speech-recognitionMetric werComparison conditions not established | 13.84 | saattrupdan Publisher reported |
Evaluated revision not stated | — |
| Danish Common Voice 8.0 | Task automatic-speech-recognitionMetric werComparison conditions not established | 17.91 | saattrupdan Publisher reported |
Evaluated revision not stated | — |
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 wav2vec2-xls-r-300m-ftspeech
Transcribing the Danish parliament is what this one was tuned for. Dan Saattrup Smart fine-tuned facebook/wav2vec2-xls-r-300m on FTSpeech, 1,800 hours of transcribed speeches from the Danish parliament, into a 315M parameter CTC recognizer. The hardware question nearly answers itself: 16-bit weights are 0.6 GB and need 0.8 GB of memory, so a single MI300X at $1.85 per hour on-demand, the cheapest slot we track, is far more card than one copy needs. We would pack it beside other work on the same GPU rather than dedicate anything to it.
The license is where to slow down. It is listed as other, and the publisher says use must adhere to a license from the Danish Parliament, so read that document before any deployment. Check the publisher-reported word error rates, 13.84 on the Alvenir ASR test set and 17.91 on Danish Common Voice 8.0, against your own audio before committing.
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-ftspeech or whisper-small?
wav2vec2-xls-r-300m-ftspeech (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-ftspeech or whisper-small?
At 4-bit, wav2vec2-xls-r-300m-ftspeech 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.