OpenNMT / OpenNMT/CTranslate2

add support for `LiteWhisperConfig`

Open
#1,869 3 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
4.7k
Forks
536
Avg merge
12h 12m
Merged PRs (30d)
4

Description

new whisper model uses configuration LiteWhisperConfig
when i try to convert with
ct2-transformers-converter --model efficient-speech/lite-whisper-large-v3-turbo --output_dir lite-whisper-large-v3-turbo-ct2 --trust_remote_code
i get

ValueError: No conversion is registered for the model configuration LiteWhisperConfig (supported configurations are: BartConfig, BertConfig, BloomConfig, CodeGenConfig, DistilBertConfig, FalconConfig, GPT2Config, GPTBigCodeConfig, GPTJConfig, GPTNeoXConfig, Gemma2Config, GemmaConfig, LlamaConfig, M2M100Config, MBartConfig, MPTConfig, MT5Config, MarianConfig, MistralConfig, MixFormerSequentialConfig, OPTConfig, PegasusConfig, Phi3Config, PhiConfig, RWConfig, T5Config, Wav2Vec2BertConfig, Wav2Vec2Config, WhisperConfig, XLMRobertaConfig)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by running the reported ct2-transformers-converter command with efficient-speech/lite-whisper-large-v3-turbo and inspect how the existing WhisperConfig conversion is registered. Determine the conversion changes required for LiteWhisperConfig; the work is done when this model converts successfully without the unsupported-configuration error.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface
Domain
cli, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.