Open-weight model
yaw-asr-twi-en-v13b
by Prince Nasamu Alhassan PrinceAlhassanNasamu/yaw-asr-twi-en-v13b
yaw-asr-twi-en-v13b is an open-weight model from Prince Nasamu Alhassan. It has 316M parameters. At 16-bit it needs about 0.8 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve yaw-asr-twi-en-v13b (316M 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 | 0.6 GB | 0.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 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.
yaw-asr-twi-en-v13b on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Wav2Vec2ForCTC
- Layers
- 24
- Hidden size
- 1,024
- Feed-forward size
- 4,096
- Attention heads
- 16
- Vocabulary size
- 71
- Model type
- wav2vec2
Identity and Version
- Repository
- PrinceAlhassanNasamu/yaw-asr-twi-en-v13b
- Publisher
- Prince Nasamu Alhassan
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 316M parameters
- Languages
- Not stated by the source
- Revision
- 9e7b41502b5a52a0380597324c63935f930045f2
- First published
- 2026-10-05
- Last updated
- 2026-10-06
Files and Weights
22 files, 5.0 GB in total. The weights are 7 files totalling 5.0 GB in bin, pt, pth, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.3 GB | a92a65cfb26f |
| trainer_ckpt/checkpoint-5733/model.safetensors | Weights | 1.3 GB | a92a65cfb26f |
| trainer_ckpt/checkpoint-5733/optimizer.pt | Weights | 2.5 GB | 5ab206ea6aa6 |
| trainer_ckpt/checkpoint-5733/rng_state.pth | Weights | 14.6 KB | 7eb4bbb97f24 |
| trainer_ckpt/checkpoint-5733/scaler.pt | Weights | 1.4 KB | bc8444fd2537 |
| trainer_ckpt/checkpoint-5733/scheduler.pt | Weights | 1.5 KB | 5ae4ec13024d |
| trainer_ckpt/checkpoint-5733/training_args.bin | Weights | 5.8 KB | be7aa3c065ae |
| config.json | Configuration | 2.0 KB | — |
| eval_pairs.json | Configuration | 1.0 MB | — |
| eval_yaw101.json | Configuration | 2.9 KB | — |
| mixture.json | Configuration | 1.1 KB | — |
| preprocessor_config.json | Configuration | 256 B | — |
| special_tokens_map.json | Configuration | 94 B | — |
| trainer_ckpt/checkpoint-5733/config.json | Configuration | 2.0 KB | — |
| trainer_ckpt/checkpoint-5733/preprocessor_config.json | Configuration | 256 B | — |
| trainer_ckpt/checkpoint-5733/special_tokens_map.json | Configuration | 94 B | — |
| trainer_ckpt/checkpoint-5733/trainer_state.json | Configuration | 41.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer_config.json | Tokenizer | 952 B | — |
| trainer_ckpt/checkpoint-5733/tokenizer_config.json | Tokenizer | 952 B | — |
| trainer_ckpt/checkpoint-5733/vocab.json | Tokenizer | 805 B | — |
| vocab.json | Tokenizer | 805 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 5.0 GB
Released by Prince Nasamu Alhassan through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 5.0 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About yaw-asr-twi-en-v13b
How much GPU memory does yaw-asr-twi-en-v13b need?
About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (316M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run yaw-asr-twi-en-v13b 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.