[HF][streaming][3/n] Text2Speech (no streaming, but updating docs on …

…completion params)

Ok this one is weird. Today, streaming is only ever supported on text outputs in Transformers library. See `BaseStreamer` in here: https://github.com/search?q=repo%3Ahuggingface%2Ftransformers%20BaseStreamer&type=code

In the future it may support other formats, but not yet. For example, OpenAI supports it: https://community.openai.com/t/streaming-from-text-to-speech-api/493784

Anyways, I basically here only did some updates to docs to clarify why completion params were null. Jonathan and I synced about this briefly ofline, but I forgot again so wanted to capture it here so no one forgets

extensions/HuggingFace/python/src/aiconfig_extension_hugging_face/local_inference/text_2_speech.py

@@ -25,6 +25,8 @@
 
 # Step 1: define Helpers
 def refine_pipeline_creation_params(model_settings: Dict[str, Any]) -> List[Dict[str, Any]]:
+ # There are from the transformers Github repo: 
+ # https://github.com/huggingface/transformers/blob/main/src/transformers/modeling_utils.py#L2534
  supported_keys = {
  "torch_dtype",
  "force_download",
@@ -61,9 +63,11 @@ def refine_pipeline_creation_params(model_settings: Dict[str, Any]) -> List[Dict
 
 
 def refine_completion_params(unfiltered_completion_params: Dict[str, Any]) -> Dict[str, Any]:
- supported_keys = {
- # ???
- }
+ # Note: There seems to be no public API docs on what completion
+ # params are supported for text to speech: 
+ # https://huggingface.co/docs/transformers/tasks/text-to-speech#inference
+ # The only one mentioned is `forward_params` which can contain `speaker_embeddings`
+ supported_keys = {}
 
  completion_params: Dict[str, Any] = {}
  for key in unfiltered_completion_params: