mdimamhosen/bangla-whistle
automatic-speech-recognition model by mdimamhosen
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A compact Bangla automatic speech recognition checkpoint. The model has 15,968,768 parameters and the float32 checkpoint is 63,944,321 bytes. This model card reports the saved rslt3 run only. Lower CER and WER are better. OpenSLR 53 archive f is held out from training but belongs to the same corpus. FLEURS and Common Voice are external test sets. The paired mean utterance-CER gap (rslt3 minus the baseline), with stored 95% bootstrap interval, is −0.133 [−0.174, −0.091] on OpenSLR, +0.260 [+0.251, +0.268] on FLEURS, and +0.184 [+0.181, +0.188] on Common Voice. The baseline is ahead on both external tests. RTF values are specific to the recorded evaluation environment and are not a service latency guarantee. Install Python 3.11 or newer, PyTorch, Transformers, NumPy, and FFmpeg, then run from this directory: The CLI converts to 16 kHz mono with FFmpeg, truncates input at 30 seconds, and uses beam width five. The model is…
Read the full model card ↗ · Preview checked 2026-10-30T01:00:21.889Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: cc-by-sa-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
mdimamhosen/bangla-whistle is a automatic-speech-recognition model repository published by mdimamhosen on Hugging Face. A library was not reported.
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
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- cc-by-sa-4.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-25T06:37:11.000Z
- Last modified
- 2026-10-25T06:37:48.000Z
Compatibility and lineage
Reported languages: bn
Base-model lineage was not included.
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 2026-10-25T06:46:38.979Z. 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