config: map AutoModelForTextToWaveform so pipeline() resolves
Same fix as rumik-ai/rumik-oss-1#3.
pipeline("text-to-speech", model="rumik-ai/rumik-oss-1-base", trust_remote_code=True) fails with:
ValueError: Unrecognized configuration class RumikOSSConfig for this kind of
AutoModel: AutoModelForTextToWaveform
That snippet is the one the Hub auto-generates from pipeline_tag, so it is the first thing most users run.
Cause. The TTS pipeline asks for AutoModelForTextToWaveform. auto_map declared only AutoConfig and AutoModelForCausalLM, so transformers fell back to its built-in config->model table, which has no rumik_oss entry.
Change. One line, pointing that Auto class at the existing RumikOSSForCausalLM (confirmed as this repo's architectures entry). No new code, no new file. The model emits audio tokens; Mimi decoding stays the caller's job.
Note. On transformers 5.x the pipeline then hits an upstream bug (BatchEncoding.to() got an unexpected keyword argument 'dtype', text_to_audio.py) that also breaks suno/bark-small. Not fixable here.
Thanks for investigating the loading error. This mapping is not sufficient for TTS pipeline support, so please hold the merge.
RumikOSSForCausalLMreturns token IDs, whereasAutoModelForTextToWaveformpromises a waveform. In Transformers 4.57.6,TextToAudioPipeline.postprocess()simply casts these IDs to float and returns them underaudio; it never invokes Mimi. I reproduced this postprocessing behavior with a CPU-only test using the installed pipeline source, not a full checkpoint inference test.- The pipeline calls inherited
generate(), not ourgenerate_audio(). It therefore bypasses the custom audio-vocabulary restriction and learned stop predictor. Ordinary pipeline preprocessing also does not construct our speaker/text/audio prompt.
A complete fix needs a dedicated waveform adapter or custom pipeline that constructs the prompt, calls generate_audio(), removes the input prefix, recovers codec frames, and decodes through the bundled Mimi codec, returning actual audio at 24 kHz. Please retain the existing causal-LM interface unchanged. Both releases need end-to-end waveform tests on explicitly supported Transformers versions before merging. The reported Transformers 5.x error is separate from these issues; removing the loading error alone does not establish compatibility.