MCPcopy Create free account

hub / github.com/OpenMOSS/MOSS-TTS / functions

Functions1,298 in github.com/OpenMOSS/MOSS-TTS

⨍ Functions 1,298◇ Types & classes 178↳ Endpoints 16
↓ 215 callersMethodget
(self, session_id: str)
moss_tts_realtime/fast_api.py:531
↓ 207 callersMethodto
(self, *args, **kwargs)
moss_soundeffect_v2/diffsynth/utils/__init__.py:32
↓ 58 callersMethodget
(self)
clis/moss_tts_local_v1.5_app.py:290
↓ 56 callersMethodupdate
(self, **kwargs: Any)
clis/moss_tts_local_v1.5_app.py:339
↓ 44 callersMethodload
(cls, path)
moss_soundeffect_v2/diffsynth/models/dac_vae.py:50
↓ 42 callersMethodencode
(self, waveform, n_quantizers=N_QUANTIZERS)
moss_tts_delay/llama_cpp/pipeline.py:104
↓ 37 callersMethodfrom_pretrained
(cls, *args, **kwargs)
moss_tts_local/modeling_moss_tts.py:625
↓ 36 callersMethodget
(self, data_id: int)
moss_soundeffect_v2/diffsynth/trainers/cache_shards.py:265
↓ 33 callersMethodupdate
(self, hidden_states)
moss_soundeffect_v2/diffsynth/pipelines/wan_audio.py:625
↓ 30 callersFunctionhash_state_dict_keys
(state_dict, with_shape=True)
moss_soundeffect_v2/diffsynth/models/utils.py:179
↓ 16 callersMethodkeys
(self)
scripts/fuse_moss_tts_delay_with_codec.py:63
↓ 15 callersMethodsnapshot
Take a snapshot. Returns current device-level GPU used MB.
moss_tts_delay/llama_cpp/gpu_monitor.py:140
↓ 14 callersMethodsave
(self, path)
moss_soundeffect_v2/diffsynth/models/dac_vae.py:31
↓ 13 callersMethodtokenizer
(self)
moss_soundeffect_v2/pipeline_moss_soundeffect.py:68
↓ 11 callersFunction_get_special_token_str
(tokenizer: Tokenizer, token_id: int)
moss_tts_delay/llama_cpp/processor.py:63
↓ 11 callersMethoddecode
(self, audio_codes, n_quantizers=N_QUANTIZERS)
moss_tts_delay/llama_cpp/pipeline.py:133
↓ 11 callersFunctionformat_timestamp
()
moss_tts_local_v1.5/finetuning/common.py:151
↓ 11 callersMethodnorm
(self, x)
moss_soundeffect_v2/diffsynth/models/wan_video_dit.py:127
↓ 10 callersMethod_encode_text
(self, text: str)
moss_tts_local_v1.5/processing_moss_tts.py:319
↓ 10 callersMethoddevice
(self)
moss_tts_local_v1.5/streaming.py:579
↓ 10 callersFunctionload_json
(path: Path)
scripts/fuse_moss_tts_delay_with_codec.py:82
↓ 10 callersMethodstart
(self)
moss_tts_realtime/app.py:667
↓ 10 callersMethodstep
( self, text_token: Optional[Iterable[int] | torch.Tensor | int], temperature: float =
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:241
↓ 9 callersFunctionWNConv1d
(*args, **kwargs)
moss_soundeffect_v2/diffsynth/models/dac_vae.py:307
↓ 9 callersMethodbuild_user_message
( text: Optional[str] = None, reference: Optional[List[Optional[Union[str, torch.Tensor]]]] =
moss_tts_local/processing_moss_tts.py:381
↓ 9 callersFunctionnormalize_audio_path_list
( value: Any, field_name: str, *, allow_none: bool = False, base_dir: Optional[Path] = Non
moss_tts_local_v1.5/finetuning/common.py:103
↓ 9 callersFunctionrequire_json_object
(value: object, context: str)
scripts/fuse_moss_tts_delay_with_codec.py:103
↓ 9 callersMethodto_dict
(self)
moss_tts_local/processing_moss_tts.py:49
↓ 8 callersMethod__init__
(self, num_inference_steps, rel_l1_thresh, model_id)
moss_soundeffect_v2/diffsynth/pipelines/wan_audio.py:579
↓ 8 callersMethod__init__
( self, encoder_dim: int = 64, encoder_rates: List[int] = [2, 4, 8, 8], latent
moss_soundeffect_v2/diffsynth/models/dac_vae.py:805
↓ 8 callersMethod__init__
(self, in_dim, out_dim, has_pos_emb=False)
moss_soundeffect_v2/diffsynth/models/wan_video_dit.py:255
↓ 8 callersMethod_set_state
( self, *, state: str | None = None, progress: float | None = None, me
moss_tts_realtime/app.py:685
↓ 8 callersMethoddevice
Get the device of the model parameters.
moss_soundeffect_v2/diffsynth/models/dac_vae.py:870
↓ 8 callersFunctionnormalize_audio_path_list
( value: Any, field_name: str, allow_none: bool = False, )
moss_tts_local/finetuning/common.py:103
↓ 8 callersFunctionnormalize_audio_path_list
( value: Any, field_name: str, allow_none: bool = False, )
moss_tts_delay/finetuning/common.py:103
↓ 8 callersMethodrun
(self, model_fn, sliding_window_size, sliding_window_stride, computation_device, computation_dtype, model_kwar
moss_soundeffect_v2/diffsynth/pipelines/wan_audio.py:653
↓ 7 callersMethod_build_text_rows
(self, token_ids: Sequence[int], *, device: Optional[torch.device] = None)
moss_tts_local_v1.5/processing_moss_tts.py:325
↓ 7 callersMethodclose
(self)
moss_tts_delay/llama_cpp/pipeline.py:120
↓ 7 callersMethoddecode_frames
(self, audio_frames: list[torch.Tensor])
moss_tts_realtime/app.py:211
↓ 7 callersFunctionformat_timestamp
()
moss_tts_local/finetuning/sft.py:178
↓ 7 callersFunctionformat_timestamp
()
moss_tts_delay/finetuning/sft.py:179
↓ 7 callersMethodfrom_pretrained
(cls, pretrained_model_name_or_path, *args, **kwargs)
moss_tts_local_v1.5/processing_moss_tts.py:212
↓ 7 callersMethodpush_text_tokens
(self, tokens: Iterable[int])
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:618
↓ 7 callersMethodreset_turn
( self, user_text: Optional[str] = None, user_audio_tokens: Optional[np.ndarray] = Non
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:587
↓ 6 callersMethod__init__
(self, config: MossTTSRealtimeLocalTransformerConfig)
moss_tts_realtime/mossttsrealtime/modeling_mossttsrealtime_local.py:271
↓ 6 callersMethod_emit_audio_chunks
( self, sess: SessionRuntime, chunks: Iterator[np.ndarray], )
moss_tts_realtime/fast_api.py:604
↓ 6 callersFunction_normalize_template_value
(value: Any)
moss_tts_local_v1.5/processing_moss_tts.py:59
↓ 6 callersFunctioncreate_custom_forward
(module)
moss_soundeffect_v2/diffsynth/pipelines/wan_audio.py:821
↓ 6 callersMethoddrain
(self, max_steps: Optional[int] = None)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:636
↓ 6 callersMethodencode
Encode given audio data and return quantized latent codes Parameters ---------- audio_data : Tensor[B x 1 x T] Au
moss_soundeffect_v2/diffsynth/models/dac_vae.py:888
↓ 6 callersMethodend_text
(self)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:629
↓ 6 callersFunctionformat_timestamp
()
moss_tts_realtime/finetuning/sft.py:166
↓ 6 callersMethodfrom_pretrained
(cls, pretrained_model_name_or_path, *args, **kwargs)
moss_tts_delay/processing_moss_tts.py:195
↓ 6 callersMethodload_models_to_device
(self, model_names=[])
moss_soundeffect_v2/diffsynth/utils/__init__.py:93
↓ 6 callersFunctionnormalize_audio_codes
(value: Any, field_name: str)
moss_tts_local/finetuning/dataset.py:25
↓ 6 callersFunctionnormalize_audio_codes
(value: Any, field_name: str)
moss_tts_delay/finetuning/dataset.py:25
↓ 6 callersFunctionnormalize_audio_codes
(value: Any, field_name: str)
moss_tts_local_v1.5/finetuning/dataset.py:23
↓ 6 callersFunctionprecompute_freqs_cis
(dim: int, end: int = 16384, theta: float = 10000.0, s: float = 1.0)
moss_soundeffect_v2/diffsynth/models/wan_audio_dit.py:47
↓ 6 callersFunctionrequire_json_int
(value: object, context: str)
scripts/fuse_moss_tts_delay_with_codec.py:114
↓ 5 callersMethod__init__
( self, input_size: int, ffn_hidden_size: int, output_size: int, bias:
moss_tts_local/modeling_moss_tts.py:59
↓ 5 callersMethod__init__
(self, config)
moss_tts_local_v1.5/qwen3_decoder.py:108
↓ 5 callersMethod_consume_audio
(chunks: Iterator[np.ndarray])
moss_tts_realtime/app.py:706
↓ 5 callersFunction_safe_int
(value: Any, *, default: int, minimum: int, maximum: int | None = None)
clis/moss_tts_local_v1.5_app.py:149
↓ 5 callersMethod_sample_next_token
( self, logits: torch.FloatTensor, do_sample: bool, temperature: float,
moss_tts_local_v1.5/modeling_moss_tts.py:394
↓ 5 callersMethodaudio_chunks
(self)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:773
↓ 5 callersMethodbuild_assistant_message
( audio_codes_list: List[Union[str, torch.Tensor]], content: str = AUDIO_PLACEHOLDER, )
moss_tts_local/processing_moss_tts.py:405
↓ 5 callersMethodbuild_user_message
( text: Optional[str] = None, reference: Optional[List[Optional[Union[str, os.PathLike, torch.
moss_tts_local_v1.5/processing_moss_tts.py:280
↓ 5 callersMethoddecode
Decode given latent codes and return audio data Parameters ---------- z : Tensor[B x D x T] Quantized continuous
moss_soundeffect_v2/diffsynth/models/dac_vae.py:932
↓ 5 callersMethoddecode_frames
(self, audio_frames: list[torch.Tensor])
moss_tts_realtime/fast_api.py:140
↓ 5 callersMethodget_tensor
(self, key: str)
scripts/fuse_moss_tts_delay_with_codec.py:65
↓ 5 callersMethodmake_ensemble
(self, prompt_audio_tokens=None)
moss_tts_realtime/inferencer.py:34
↓ 5 callersMethodpush_tokens
(self, audio_tokens: np.ndarray | torch.Tensor)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:759
↓ 5 callersFunctionrequire_weight_map
(index: JSONDict, context: str)
scripts/fuse_moss_tts_delay_with_codec.py:178
↓ 5 callersMethodreset_generation_state
(self, keep_cache: bool = True)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:108
↓ 5 callersMethodstep
(self, scheduler, latents, progress_id, noise_pred, input_latents=None, inpaint_mask=None, **kwargs)
moss_soundeffect_v2/diffsynth/utils/__init__.py:147
↓ 4 callersMethod__init__
(self, config: GPT2Config)
moss_tts_local_v1.5/gpt2_decoder.py:85
↓ 4 callersMethod_decode_audio_frames
(self, audio_frames: list[torch.Tensor])
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:1014
↓ 4 callersMethod_decode_local_hidden_states_with_cache
( self, local_inputs_embeds: torch.FloatTensor, past_key_values: Optional[tuple[Any, .
moss_tts_local_v1.5/modeling_moss_tts.py:231
↓ 4 callersFunction_ensure_dir
(path: str)
moss_soundeffect_v2/diffsynth/trainers/cache_shards.py:28
↓ 4 callersMethod_safe_put_audio_end
(self, sess: SessionRuntime)
moss_tts_realtime/fast_api.py:585
↓ 4 callersFunction_to_tensor
(value: Any, device: torch.device, dtype: torch.dtype)
community/norwegian-lora/train_lora.py:300
↓ 4 callersMethod_use_binary_local_text_head
(self)
moss_tts_local_v1.5/modeling_moss_tts.py:136
↓ 4 callersMethoddevice
(self)
moss_tts_realtime/inferencer.py:90
↓ 4 callersMethodemit_many
(self, chunks: Iterator[np.ndarray], message_prefix: str)
moss_tts_realtime/app.py:251
↓ 4 callersMethodencode_audios_from_path
( self, wav_path_list: Union[str, os.PathLike, list[Union[str, os.PathLike]]], n_vq: O
moss_tts_local_v1.5/processing_moss_tts.py:850
↓ 4 callersMethodfinish
(self)
moss_tts_realtime/fast_api.py:133
↓ 4 callersMethodflush
(self)
moss_tts_realtime/app.py:231
↓ 4 callersMethodfrom_pretrained
Load a WanAudioPipeline from a HuggingFace-format directory. Expected layout (a diffusers-style HF model directory): model_dir/
moss_soundeffect_v2/diffsynth/pipelines/wan_audio.py:190
↓ 4 callersMethodgenerate
( self, input_ids: torch.LongTensor, attention_mask: Optional[torch.Tensor] = None,
moss_tts_local/modeling_moss_tts.py:708
↓ 4 callersFunctionnormalize_audio_path_list
( value: Any, field_name: str, allow_none: bool = False, )
moss_tts_realtime/finetuning/common.py:103
↓ 4 callersMethodprocess
(self, pipe: BasePipeline, inputs: dict, positive=True, **kwargs)
moss_soundeffect_v2/diffsynth/utils/__init__.py:175
↓ 4 callersFunctionrepeat_kv
(hidden_states: torch.Tensor, n_rep: int)
moss_tts_local_v1.5/qwen3_decoder.py:99
↓ 4 callersFunctionsave_file
(tensors: dict[str, torch.Tensor], filename: str)
scripts/fuse_moss_tts_delay_with_codec.py:78
↓ 4 callersMethodset_voice_prompt_tokens
(self, audio_tokens: np.ndarray)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:530
↓ 4 callersMethodstatus
(self)
clis/moss_tts_local_v1.5_app.py:237
↓ 4 callersMethodto_dict
(self)
moss_tts_local_v1.5/processing_moss_tts.py:90
↓ 3 callersMethod_assistant_prompt_prefix_ids
(self)
moss_tts_local_v1.5/processing_moss_tts.py:367
↓ 3 callersMethod_build_inputs_embeds
(self, input_ids: torch.LongTensor)
moss_tts_local_v1.5/modeling_moss_tts.py:177
↓ 3 callersFunction_build_prompt_fields
(request: StreamingRequest)
moss_tts_local_v1.5/streaming.py:255
↓ 3 callersFunction_drain_decoder_outputs
(*, block: bool = False)
moss_tts_local_v1.5/streaming.py:861
next →1–100 of 1,298, ranked by callers