An ELARSpeech automatic speech recognition model for Belait. Input audio must be mono, sampled at 16 kHz. Whisper uses an ELARSpeech language token in the explicit decoder prompt. Use the prompt above rather than language= to reproduce the exported model's decoding behavior. The exported artifact is checked against the original ELARSpeech checkpoint on a fixed evaluation sample set. Exact-transcription verification status: PASS. This is a single-language ASR model. Accuracy can vary by recording conditions, speaker population, orthography, and domain. Resample input audio to 16 kHz mono. Please cite ELARSpeech and the base model above when using this model. See the ELARSpeech project…
Open-weight model · Speech recognition
ELARSpeech-Whisper-Large-v3-bfn
by Sangmin Lee Sanghyang00/ELARSpeech-Whisper-Large-v3-bfn
ELARSpeech-Whisper-Large-v3-bfn is an open-weight model for speech recognition from Sangmin Lee. It has 1.5B parameters. At 16-bit it needs about 3.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
An ELARSpeech automatic speech recognition model for Bunak. Input audio must be mono, sampled at 16 kHz. Whisper uses an ELARSpeech language token in the explicit decoder prompt.
Parameters1.5B
Context—
Weights6.2 GB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve ELARSpeech-Whisper-Large-v3-bfn (1.5B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 3.1 GB | 3.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.5 GB | 1.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
ELARSpeech-Whisper-Large-v3-bfn on every accelerator the SAVRN Index prices, at every precision
Model Card
An ELARSpeech automatic speech recognition model for Bunak. Input audio must be mono, sampled at 16 kHz. Whisper uses an ELARSpeech language token in the explicit decoder prompt. Use the prompt above rather than language= to reproduce the exported model's decoding behavior. The exported artifact is checked against the original ELARSpeech checkpoint on a fixed evaluation sample set. Exact-transcription verification status: PASS. This is a single-language ASR model. Accuracy can vary by recording conditions, speaker population, orthography, and domain. Resample input audio to 16 kHz mono. Please cite ELARSpeech and the base model above when using this model. See the ELARSpeech project…
Excerpt from the card by Sangmin Lee.
Configuration
- Architecture
- WhisperForConditionalGeneration
- Vocabulary size
- 51,867
- Model type
- whisper
Identity and Version
- Repository
- Sanghyang00/ELARSpeech-Whisper-Large-v3-bfn
- Publisher
- Sangmin Lee
- Task
- Speech recognition
- Modality
- Audio
- Library
- transformers
- Parameters
- 1.5B parameters
- Languages
- bfn
- Revision
- a1bf74dc7d91c8da7f657516a081c14e326f8906
- First published
- 2026-10-15
- Last updated
- 2026-10-15
Files and Weights
11 files, 6.2 GB in total. The weights are 2 files totalling 6.2 GB in safetensors.
Weights2 files · 6.2 GB
Configuration5 files · 125.1 KB
Tokenizer2 files · 3.9 MB
Documentation1 file · 2.3 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00002.safetensors | Weights | 5.0 GB | 7e71ce5bac41 |
| model-00002-of-00002.safetensors | Weights | 1.2 GB | 287405816697 |
| config.json | Configuration | 1.2 KB | — |
| elarspeech_export.json | Configuration | 9.0 KB | — |
| generation_config.json | Configuration | 2.9 KB | — |
| model.safetensors.index.json | Configuration | 111.6 KB | — |
| processor_config.json | Configuration | 410 B | — |
| README.md | Documentation | 2.3 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 3.9 MB | — |
| tokenizer_config.json | Tokenizer | 551 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 6.2 GB
Download from Sangmin Lee
Released by Sangmin Lee through its official repository on Hugging Face.
Built From
- Derived from openai/whisper-large-v3
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.2 GB |
| 16-bit | 3.1 GB |
| 8-bit | 1.5 GB |
| 4-bit | 0.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About ELARSpeech-Whisper-Large-v3-bfn
How much GPU memory does ELARSpeech-Whisper-Large-v3-bfn need?
About 3.7 GB at 16-bit and 0.9 GB at 4-bit: the weights (1.5B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run ELARSpeech-Whisper-Large-v3-bfn on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Similar Models
An ELARSpeech automatic speech recognition model for Bastimentos Creole English. Input audio must be mono, sampled at 16 kHz. Whisper uses an ELARSpeech language token in the explicit decoder prompt. Use the prompt above rather than language= to reproduce the exported model's decoding behavior. The exported artifact is checked against the original ELARSpeech checkpoint on a fixed evaluation sample set. Exact-transcription verification status: PASS. This is a single-language ASR model. Accuracy can vary by recording conditions, speaker population, orthography, and domain. Resample input audio to 16 kHz mono. Please cite ELARSpeech and the base model above when using this model. See the…
An ELARSpeech automatic speech recognition model for Waimaha. Input audio must be mono, sampled at 16 kHz. Whisper uses an ELARSpeech language token in the explicit decoder prompt. Use the prompt above rather than language= to reproduce the exported model's decoding behavior. The exported artifact is checked against the original ELARSpeech checkpoint on a fixed evaluation sample set. Exact-transcription verification status: PASS. This is a single-language ASR model. Accuracy can vary by recording conditions, speaker population, orthography, and domain. Resample input audio to 16 kHz mono. Please cite ELARSpeech and the base model above when using this model. See the ELARSpeech project…
Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting. Whisper large-v3 has the same architecture as the previous large and large-v2 models, except for the following minor differences: 1. The spectrogram input uses 128 Mel frequency bins instead of 80 The Whisper large-v3 model was trained on 1 million hours of weakly labeled audio and 4 million hours of pseudo-labeled audio collected using…
For usage instructions follow openai/whisper-large-v3. Large-v3 finetune trained as a baseline with smaller checkpoints in progress. Expecting worse long form and equal short form. Benchmarks. Has occasional repetition issue compared to previous models but achieves competitive/SOTA CER across all tested sets.
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).