ErrLookup › openai/whisper

openai/whisper

Robust Speech Recognition via Large-Scale Weak Supervision · Python · 14 source files

Analyzed at 5f86d1d863 on 2026-08-14. 16 documented errors.

Code / MessageTypeSeverityTags
Unexpected token
exception warning normalization, english, asr-postprocessing, edge-case
Language not found in tokenizer.
exception error tokenizer, language, vocabulary, configuration
exists and is not a regular file
exception error filesystem, model-download, cache, configuration
This tokenizer does not have language token configured
exception error tokenizer, language-id, multilingual, model-config
Failed to load audio
exception error audio, ffmpeg, subprocess, file-format
This model doesn't have language tokens so it can't perform…
exception error language-id, tokenizer, model-config, multilingual
model should be one of
exception error cli, argparse, model-loading, configuration
length_penalty (alpha) should be a value between 0 and 1
exception error decoding, options-validation, beam-search, range-check
Model has been downloaded but the SHA256 checksum does not…
exception error network, model-download, checksum, retry
triton import failed; try `pip install --pre triton`
exception error dependencies, triton, cuda, import-error, environment
Expected one of , got
exception error cli, argparse, boolean-parsing, configuration
Unsupported language
exception error tokenizer, language, validation, configuration
best_of with greedy sampling (T=0) is not compatible
exception error decoding, options-validation, sampling, temperature
beam_size and best_of can't be given together
exception error decoding, options-validation, beam-search
patience requires beam_size to be given
exception error decoding, options-validation, beam-search
Model not found; available models =
exception error model-loading, configuration, cli, filesystem