guillaumekln

/

faster-whisper-large-v2

like 185

I have encountered an issue while trying to host the model on the Hugging Face Inference API. I received an error message when initializing the model, and I have included the relevant logs below for your reference:

ValueError: Unrecognized model in /repository. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: albert, audio-spectrogram-transformer, bart, beit, bert, bert-generation, big_bird, bigbird_pegasus, blenderbot, blenderbot-small, bloom, camembert, canine, chinese_clip, clip, clipseg, codegen, conditional_detr, convbert, convnext, ctrl, cvt, data2vec-audio, data2vec-text, data2vec-vision, deberta, deberta-v2, decision_transformer, deformable_detr, deit, detr, dinat, distilbert, donut-swin, dpr, dpt, electra, encoder-decoder, ernie, esm, flaubert, flava, fnet, fsmt, funnel, glpn, gpt2, gpt_neo, gpt_neox, gpt_neox_japanese, gptj, groupvit, hubert, ibert, imagegpt, jukebox, layoutlm, layoutlmv2, layoutlmv3, led, levit, lilt, longformer, longt5, luke, lxmert, m2m_100, marian, markuplm, maskformer, maskformer-swin, mbart, mctct, megatron-bert, mobilebert, mobilenet_v1, mobilenet_v2, mobilevit, mpnet, mt5, mvp, nat, nezha, nystromformer, openai-gpt, opt, owlvit, pegasus, pegasus_x, perceiver, plbart, poolformer, prophetnet, qdqbert, rag, realm, reformer, regnet, rembert, resnet, retribert, roberta, roc_bert, roformer, segformer, sew, sew-d, speech-encoder-decoder, speech_to_text, speech_to_text_2, splinter, squeezebert, swin, swinv2, switch_transformers, t5, table-transformer, tapas, time_series_transformer, trajectory_transformer, transfo-xl, trocr, unispeech, unispeech-sat, van, videomae, vilt, vision-encoder-decoder, vision-text-dual-encoder, visual_bert, vit, vit_mae, vit_msn, wav2vec2, wav2vec2-conformer, wavlm, whisper, xclip, xglm, xlm, xlm-prophetnet, xlm-roberta, xlm-roberta-xl, xlnet, yolos, yoso ```

Based on the error message, it seems that the model configuration may be missing a model_type key in its config.json file or does not contain a recognizable model name.

Shall I try to contribute to the project or do you want to take a look 

@guillaumekln

	 ?