Open-weight model
wavlm-large-s3t2ss-libri960-ce-segmentation
by Kevingeng Haopeng/wavlm-large-s3t2ss-libri960-ce-segmentation
wavlm-large-s3t2ss-libri960-ce-segmentation is an open-weight model from Kevingeng. It has 317M 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.
This repository exports the checkpoint used as “Ours 10ms” in the historical LibriSpeech → TIMIT segmentation comparison.
Runs On
What it takes to serve wavlm-large-s3t2ss-libri960-ce-segmentation (317M 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.
Model Card
This repository exports the checkpoint used as “Ours 10ms” in the historical LibriSpeech → TIMIT segmentation comparison. It includes the full trained WavLM backbone, projection, FiLM module, recognition heads, labels, and an explicitly frozen encoder adapter for PRiSM representation probing. The final checkpoint is epoch 3 / step 450 of a Libri100 alignment-CE refinement initialized from a Libri960 Subphonetic OTTC curriculum. It is not the later Libri960 recognition-PER-best epoch-17 model, and it is not an OTTC-only final stage. 中文说明：这是此前 segmentation 主表中的 S3T2 + FiLM 版本。训练链包括 Libri960 阶段和后续 Libri100 CE 校准；Libri100 是 Libri960 的子集。上传时保留 完整表示网络，供 PRiSM 冻结编码器、训练新的下游预测头。原始识别 logits 不是 PRiSM…
Excerpt from the card by Kevingeng.
Identity and Version
- Repository
- Haopeng/wavlm-large-s3t2ss-libri960-ce-segmentation
- Publisher
- Kevingeng
- Task
- Not stated by the source
- Modality
- Other
- Library
- pytorch
- Parameters
- 317M parameters
- Languages
- en
- Revision
- fe283d153cbe757866f407a584ddb91f7db3133b
- First published
- 2026-09-22
- Last updated
- 2026-09-22
Files and Weights
12 files, 1.3 GB in total. The weights are 1 file totalling 1.3 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.3 GB | efa852371e8d |
| config.json | Configuration | 3.3 KB | — |
| labels.json | Configuration | 8.1 KB | — |
| metrics.json | Configuration | 4.1 KB | — |
| prism_example.py | Configuration | 1.4 KB | — |
| provenance.json | Configuration | 1.6 KB | — |
| spottc.py | Configuration | 9.1 KB | — |
| validation.json | Configuration | 908 B | — |
| README.md | Documentation | 10.5 KB | — |
| SHA256SUMS | Other | 801 B | — |
| requirements.txt | Other | 106 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.3 GB
Released by Kevingeng through its official repository on Hugging Face.
Built From
- Derived from microsoft/wavlm-large
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.3 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 wavlm-large-s3t2ss-libri960-ce-segmentation
How much GPU memory does wavlm-large-s3t2ss-libri960-ce-segmentation need?
About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (317M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run wavlm-large-s3t2ss-libri960-ce-segmentation 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.