Model reference · open weights

wav2vec2-bloom-speech-tgl

Audio sil-ai Speech→text 1 build Its own licence terms 2k dl/mo

wav2vec2-bloom-speech-tgl is an open-weight audio or speech model from sil-ai. wav2vec2-bloom-speech-tgl (BF16) weighs 1.3 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • wav2vec2-bloom-speech-tgl is an automatic speech recognition model developed by sil-ai for the Tagalog language.
  • It is a fine-tuned version of facebook/wav2vec2-xls-r-300m trained on the SIL-AI/bloom-speech dataset.
  • The model is distributed under the SIL RAIL-M License and is described as a proof of concept.

Summary of the sil-ai/wav2vec2-bloom-speech-tgl model card, 2026-10-01

What it is

Released bysil-ai
Released2022-06-15
VRAM1.3 GB for the weights

What it runs on

Memory and cards for wav2vec2-bloom-speech-tgl (BF16)

1.3 GBweights, file size
1.6 GBruntime overhead
CardOne streamMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Benchmarks

Reported results

As published on the model card: the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Speech RecognitionBloom Speech tglTest WER24.570
Speech RecognitionBloom Speech tglTest CER7.690
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms