Skip to main content

AI models that run on this device.

Two small chat models run in a computer’s browser here; every other model is a file you download.

BuzzASR

bengali

BuzzASR/bengali
Model details
speech recognitionLicense: mitSHA-256 recorded for 9 of 12 filessafetensors

Content controls: not assessed.

The catalog lists this model for transcribing speech. Catalog sources: license, cardMetadata.license, baseModel, task, cardMetadata.pipelineTag.

Quick answer: compatibility and sources

Can I run bengali on my computer?

It depends on your memory, processor, file format and runtime. Hugging Bay offers 9 hosted files; check the file list for the exact selection. A file-size fit is an estimate, not a successful run or speed promise. Read the license before use.

bengali is an open-weights audio model for speech recognition. Model weights are learned parameters; a runtime loads them. A hosted file is an individual file Hugging Bay can serve. SHA-256 identifies exact file bytes. The availability date above applies to this file record, not the upstream metadata update date.

As of the recorded file availability check on .

Recorded SHA-256 for model.safetensors: 372d920540086f4cc153ce5032dbd1f50489b60f76803e9fb879417b003e454e. Exact file evidence · Machine-readable source facts · Run evidence and any recorded receipts. A checksum fingerprints only the named file bytes; it does not prove safety, quality, a complete multi-file selection or a successful run.

Updated · Page-copy source revision 8871bab84e1cf80aea1686a944ec335078a6c036 · Source files: apps/web/lib/model-page-template.mjs, apps/web/lib/model-page-v3.mjs, apps/web/lib/aeo-page.mjs · Full revision record

Model metadata: As of at the model source. Popularity counters are source-reported, not measured by Hugging Bay. Availability checked .

Key facts

Catalog record
Summarizes upstream metadata; it is not itself a download or run receipt.
File evidence
Lists exact filenames, availability and any recorded SHA-256 for individual files.
Run evidence
Reports measured results only when a receipt exists for named file bytes and a setup; otherwise unmeasured.
Checksum scope
SHA-256 fingerprints one file’s bytes; it does not prove safety, quality or a multi-file bundle.

Evidence you can inspect (plain text)

  • This page’s quick answer names the file record for hf-model-buzzasr-bengali.
  • Open /artifact/hf-model-buzzasr-bengali/files for this exact filenames, availability and any recorded SHA-256.
  • Open /evidence/artifacts/hf-model-buzzasr-bengali for run-readiness evidence tied to that record; absent receipts stay unmeasured.
  • Open /api/artifacts/hf-model-buzzasr-bengali/card.md for machine-readable source facts (not a runtime test).
  • A matching checksum on this page fingerprints only the named bytes shown in file evidence.

Unmeasured states are stated explicitly; this page does not invent run scores or compatibility guarantees.

Which date applies to which fact

  • File availability check:
  • Committed page-copy sources:
  • Upstream model metadata: Dates on artifact records when shown; not implied by page-copy revision
  • Run receipts: Only on /evidence pages when recorded; otherwise unmeasured

Page-copy revision (Updated line above) identifies committed text sources, not upstream model edits or test outcomes.

9 hosted of 12 listed

Hashes recorded. Date not recorded.

FileSizeSHA-256SourceDownload
Weights
model.safetensors3.09 GB
372d9205…003e454e372d920540086f4cc153ce5032dbd1f50489b60f76803e9fb879417b003e454e
HostedDownload
Tokenizer & config
added_tokens.json34.6 KB
5840436f…87185a8e5840436f80f95b6ffee84401075e63babacff0ed70ed7f240443feff87185a8e
HostedDownload
config.json1.2 KB
c8188793…957dece9c8188793274e95dc4e1d4f6e66944c1ac71d98b0aae5c2e6943dcaaa957dece9
HostedDownload
generation_config.json471 bytes
1a6989c6…991431231a6989c636e8d5af0888495ced90d60df42bdb6dc58d5bb3ee8b6c5899143123
HostedDownload
merges.txt1.64 MB
252dcd02…f6c0f52f252dcd02ef8a0ad36fe51e10ab779264de9aaea4ee368ff9596640dcf6c0f52f
HostedDownload
normalizer.json52.7 KB—Upstream onlyFile metadata
preprocessor_config.json357 bytes
654cf18d…126bd499654cf18d3e163b948ceaf9766da56ce0b52de265d58673cf61c9376f126bd499
HostedDownload
special_tokens_map.json2.19 KB
baea4ea0…739c3e74baea4ea09372eb4fca86b4e4346139fd73cb807d5087e9de0948e971739c3e74
HostedDownload
tokenizer_config.json282.9 KB
3a9bcb48…4acd0ff53a9bcb48f21bb1037135335cc6e527840dac0e50c0ad37d7e01f28504acd0ff5
HostedDownload
vocab.json2.22 MB
5d2239ce…312cdc8b5d2239ce77c681e4c2fa422d066de8841e549a519572b7e7842c5017312cdc8b
HostedDownload
Docs
.gitattributes1.52 KB—Upstream onlyFile metadata
README.md2.77 KB—Upstream onlyFile metadata

Check a download

In the folder where you saved added_tokens.json, run:

macOS
shasum -a 256 -- 'added_tokens.json'
Linux
sha256sum -- 'added_tokens.json'
Windows
Get-FileHash -LiteralPath 'added_tokens.json' -Algorithm SHA256

Compare the result with the recorded SHA-256.

Similar hosted models

Explore hosted models