chanasia/Pathumma-stt-th-fastconformer-rnnt-large-openvino-int8
automatic-speech-recognition model by chanasia
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Earlier source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
An INT8 OpenVINO conversion of nectec/Pathumma-stt-th-fastconformer-rnnt-large, a Thai(-English) speech recognition model by NECTEC. It runs on CPU with only openvino, sentencepiece and numpy, with no NeMo and no PyTorch. On our test set it matches the original's accuracy and runs about 1.6× faster on the same CPU. This is an unofficial community conversion. It is not affiliated with or endorsed by NECTEC. All credit for the model goes to the original authors (see Citation). Or from the command line, with a 16 kHz mono 16-bit WAV file: For telephone audio (8 kHz), resample to 16 kHz first (e.g. soxr.resample(audio, 8000, 16000)). Transcribe one utterance at a time (split long recordings on pauses, ideally ≤ 15–30 s). dev split, with every other clip run through an 8 kHz G.711 μ-law round trip to cover telephone audio. on features normalized to roughly unit variance. It is a Python loop over the static-shape…
The latest refresh did not succeed. This is the last available preview; check the original for changes.
Read the full model card ↗ · Preview checked 2026-10-12T07:13:22.080Z
Inside the original model card — Document outline
- Pathumma STT FastConformer RNNT Large (TH): OpenVINO INT8
- Usage
- What is in this repo
- Changes from the original
- Evaluation
- Limitations
- License
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
chanasia/Pathumma-stt-th-fastconformer-rnnt-large-openvino-int8 is a automatic-speech-recognition model repository published by chanasia on Hugging Face. The source reports the openvino library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- automatic-speech-recognition
- Library
- openvino
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- cc-by-4.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-12T06:19:04.000Z
- Last modified
- 2026-10-12T06:19:22.000Z
Compatibility and lineage
Reported languages: th
Reported base models: nectec/Pathumma-stt-th-fastconformer-rnnt-large
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-12T06:41:18.150Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
jonatasgrosman/wav2vec2-large-xlsr-53-japanese