Add CSM model#36719
Merged
Merged
Conversation
Contributor
|
Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. When it is ready for review, please click the |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
Do you mind if I contribute to CSMForConditionalGeneration? It looks like it's currently empty. Or are you working on it right now? |
Collaborator
Author
|
Hey @SeungyounShin, currently, conditional generation is handled through the |
ArthurZucker
approved these changes
May 5, 2025
1 task
zucchini-nlp
pushed a commit
to zucchini-nlp/transformers
that referenced
this pull request
May 14, 2025
* draft structure * depth decoder with forward pre hook * full model forward draft * draft update * depth decoder update * ConversationalSpeechModelForCausalLM udpates * add generate * max length criteria small fix * udpate * updates * generation update * update in loss compute * conversion script * update for correct input embeddings * handle interleaved rope * update * update * update * support compile * update training * add doc * update doc * correct inits * ConversationalSpeechModel -> Csm * conf update * name update * tests CsmForCausalLMTest * convert use cached_file * conf + modeling updates * generate utils handle third dim shape * integration test * modeling + conf updates * common test handle more than 2 dims * add nested audio list utils * processing handle nested audio list * csm processing draft * mimi util * init updates * modular update * convert modular * processing update * csm tests update * generate tests handle third dim * generate utils handle third dim * propagate _get_initial_cache_position update * tied_weight_keys update + convert correctly * fix inputs_embeds * revert audio nested list * batch inference update + return audio * audio_utils update * processor update * some more integration tests * remove old test * porcessing output labels * improve * fix * update rope values with equivalent ones * conversion update * udpate tests * handle depth decoder generation config * remove default eos_token_id * make style * revert modeling_mimi * add default generation_config * remove sdpa since handled by default * make * fix conflict * fix conflicts * correct naming * correct imports * make * causal -> conditional naming * causal -> conditional naming * auto update * make * make * add doc * test update * fix weight init * audio tokens offsets as buffer * 4d mask in conditional class * make * doc update * fix causal mask * fix causal mask * doc update * doc update * add processor doc * update doc * fix 4d causal mask * update make_list_of_audio * do not default to mutable * remove duplicates * remove useless reset_parameters * use GradientCheckpointingLayer * use can_return_tuple * formatting * prepend placeholder in _sample * torch compile fix * some more fixies * convert modular * fix * default max_length in convert * handle depth decoder generation config correctly * clearer formulation * handle output_loading_info * handle softmax warning * add doc * propagate _get_initial_cache_position changes * generation in its own module * add processor tests * fix compile witu cuda graphs * fix compile with cuda graphs * add csm.md * include CSM loss * doc nit * doc nit * doc nit * Update docs/source/en/model_doc/csm.md Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * add save_audio to processor * Update src/transformers/models/csm/modular_csm.py Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * doc update * simplify audio_codes_mask computation * doc update * simplify loss computation * fix static cache test * fix * remove comment * simplify encoded length computation * use hf-internal-testing * doc update * cast to float before numpy * nit * mem efficient codebook head * nit * cat input values with cutoffs --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
|
Not sure if I should ask here but this implementation of csm seems considerably better quality then the official implementation for some reason? Any reason, why? |
Collaborator
|
Not sure how we should answer 😅 happy that you like it 🤗 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Adds CSM (audio)-text-to-speech model!
Original code
Hub model weights
Converted weights