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
↓ 1 callersMethod_make_backend
(self)
moss_tts_realtime/fast_api.py:487
↓ 1 callersMethod_make_generation
(self)
moss_tts_realtime/fast_api.py:496
↓ 1 callersMethod_make_streaming
(self)
moss_tts_realtime/fast_api.py:508
↓ 1 callersFunction_maybe_codec_streaming
(codec, *, batch_size: int)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:933
↓ 1 callersFunction_maybe_wait_for_buffer
(buffer_tracker: BufferedAudioTracker, threshold_seconds: float)
moss_tts_realtime/app.py:294
↓ 1 callersFunction_maybe_wait_for_buffer
(buffer_tracker: BufferedAudioTracker, threshold_seconds: float)
moss_tts_realtime/fast_api.py:165
↓ 1 callersMethod_merge_consecutive_audio_placeholders
( content: str, audio_codes_list: List[torch.Tensor], )
moss_tts_local/processing_moss_tts.py:498
↓ 1 callersMethod_merge_consecutive_audio_placeholders
( content: str, audio_codes_list: List[torch.Tensor], )
moss_tts_delay/processing_moss_tts.py:494
↓ 1 callersFunction_merge_consecutive_speaker_tags
(text: str)
clis/moss_ttsd_app.py:313
↓ 1 callersMethod_merge_heads
(self, tensor: torch.Tensor)
moss_tts_local_v1.5/gpt2_decoder.py:140
↓ 1 callersFunction_move_batch_to_device
(batch: Any, device: torch.device)
moss_tts_local_v1.5/streaming.py:165
↓ 1 callersMethod_new_static_local_past_key_values
( self, batch_size: int, max_length: int, device: torch.device, dtype:
moss_tts_local_v1.5/modeling_moss_tts.py:205
↓ 1 callersMethod_next_text_tokens
(self, text_ids_tensors: List[torch.Tensor], cur_idx: List[int], lengths: List[int])
moss_tts_realtime/inferencer.py:184
↓ 1 callersMethod_norm_token
(self, codes)
moss_tts_realtime/finetuning/dataset.py:90
↓ 1 callersFunction_normalize_audio_codes
(value, field_name)
moss_tts_realtime/finetuning/dataset.py:40
↓ 1 callersMethod_normalize_batch_inputs
( self, text: Union[str, List[str]], reference_audio_path: Optional[Union[str, List[st
moss_tts_realtime/inferencer.py:124
↓ 1 callersMethod_normalize_device
(device: Union[str, torch.device])
moss_soundeffect_v2/pipeline_moss_soundeffect.py:92
↓ 1 callersMethod_normalize_input_ids
(self, input_ids)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:119
↓ 1 callersFunction_normalize_language
(language_tag: str | None)
clis/moss_tts_local_v1.5_app.py:144
↓ 1 callersFunction_normalize_markdown_and_lines
(text: str)
moss_tts_delay/tts_robust_normalizer_single_script.py:116
↓ 1 callersMethod_normalize_message
(self, message: Union[Message, Dict])
moss_tts_local/processing_moss_tts.py:414
↓ 1 callersMethod_normalize_message
(self, message: Union[Message, Dict])
moss_tts_delay/processing_moss_tts.py:410
↓ 1 callersMethod_normalize_message
(self, message: Union[Message, Dict[str, Any]])
moss_tts_local_v1.5/processing_moss_tts.py:557
↓ 1 callersMethod_normalize_num_sequences
( cu_seqlens: torch.Tensor, num_sequences: Optional[torch.Tensor], device: torch.devic
moss_tts_local_v1.5/gpt2_decoder.py:454
↓ 1 callersFunction_normalize_prompt_text
(prompt_text: str, speaker_id: int)
clis/moss_ttsd_app.py:337
↓ 1 callersFunction_normalize_repeated_punctuation
(text: str)
moss_tts_delay/tts_robust_normalizer_single_script.py:223
↓ 1 callersFunction_normalize_seed
(value: float | int | None)
moss_tts_realtime/app.py:379
↓ 1 callersFunction_normalize_structural_punctuation
(text: str)
moss_tts_delay/tts_robust_normalizer_single_script.py:192
↓ 1 callersMethod_normalize_text_prefix
(self, text_prefix_ids, batch_size: int)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:131
↓ 1 callersFunction_nvidia_smi_device_used_mb
Fallback: parse ``nvidia-smi`` for device-level used memory.
moss_tts_delay/llama_cpp/gpu_monitor.py:85
↓ 1 callersMethod_pack_record
(self, record)
moss_tts_realtime/finetuning/dataset.py:170
↓ 1 callersMethod_pack_record
(self, record: Dict[str, Any])
moss_tts_local/finetuning/dataset.py:125
↓ 1 callersMethod_pack_record
(self, record: Dict[str, Any])
moss_tts_delay/finetuning/dataset.py:125
↓ 1 callersMethod_pack_record
(self, record: Dict[str, Any], *, index: int)
moss_tts_local_v1.5/finetuning/dataset.py:150
↓ 1 callersFunction_parse_args
()
clis/moss_tts_local_v1.5_app.py:1794
↓ 1 callersFunction_parse_args
()
moss_tts_local_v1.5/streaming.py:1032
↓ 1 callersMethod_parse_audio_codes
(self, start_length, audio_codes)
moss_tts_local/processing_moss_tts.py:688
↓ 1 callersMethod_parse_audio_codes
(self, start_length, audio_codes)
moss_tts_delay/processing_moss_tts.py:688
↓ 1 callersMethod_parse_audio_codes
( self, start_length: int, audio_codes: torch.LongTensor, *, return_st
moss_tts_local_v1.5/processing_moss_tts.py:727
↓ 1 callersFunction_parse_example_id
(example_id: str)
clis/moss_tts_app.py:73
↓ 1 callersFunction_parse_example_id
(example_id: str)
clis/moss_voice_generator_app.py:29
↓ 1 callersFunction_parse_example_id
(example_id: str)
clis/moss_tts_local_v1.5_app.py:98
↓ 1 callersMethod_parse_text_codes
(self, start_length, text_codes)
moss_tts_local/processing_moss_tts.py:663
↓ 1 callersMethod_parse_text_codes
(self, start_length, text_codes)
moss_tts_delay/processing_moss_tts.py:663
↓ 1 callersMethod_parse_text_codes
(self, start_length: int, text_codes: torch.LongTensor)
moss_tts_local_v1.5/processing_moss_tts.py:713
↓ 1 callersFunction_pcm16le_bytes
(waveform: torch.Tensor)
clis/moss_tts_local_v1.5_app.py:181
↓ 1 callersMethod_prefill
( input_ids: np.ndarray, backbone: LlamaCppBackbone, embedder: EmbeddingLookup, )
moss_tts_delay/llama_cpp/pipeline.py:673
↓ 1 callersMethod_prefill_if_needed
(self)
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:678
↓ 1 callersMethod_prepare_multi_modal_inputs
Prepares multi-modal embeddings from input_ids of shape (batch_size, channels, sequence_length). For channel 0: text + speech tokens,
moss_tts_local/modeling_moss_tts.py:516
↓ 1 callersMethod_prepare_reference
(self, reference)
moss_tts_delay/llama_cpp/pipeline.py:625
↓ 1 callersMethod_prepare_session_turn
( self, session: MossTTSRealtimeStreamingSession, processor: MossTTSRealtimeProcessor,
moss_tts_realtime/app.py:535
↓ 1 callersMethod_prepare_shifted_audio_inputs
(self, label_ids)
moss_tts_local/modeling_moss_tts.py:768
↓ 1 callersMethod_print_profile
( self, prompt_len: int, gen_steps: int, dt_prefill: float, dt_gen: fl
moss_tts_delay/llama_cpp/pipeline.py:764
↓ 1 callersFunction_prompt_overwrite_confirmation
(save_path: Path)
scripts/fuse_moss_tts_delay_with_codec.py:776
↓ 1 callersFunction_protect_spans
(text: str)
moss_tts_delay/tts_robust_normalizer_single_script.py:135
↓ 1 callersFunction_put_stream_audio
(job: StreamingJob, pcm_bytes: bytes)
clis/moss_tts_local_v1.5_app.py:438
↓ 1 callersFunction_render_user_prompt_after_reference
( language_code: object | None = None, prompt_fields: Optional[Dict[str, Any]] = None, )
moss_tts_local_v1.5/processing_moss_tts.py:66
↓ 1 callersFunction_replace_audio_placeholders
( content: str, lengths: list[int], n_vq: int, gen_slot_token: str, delay_slot_token: str,
moss_tts_delay/llama_cpp/processor.py:138
↓ 1 callersMethod_replace_audio_placeholders
( content: str, lengths: List[int], n_vq: int, gen_slot_token: str, de
moss_tts_local/processing_moss_tts.py:458
↓ 1 callersMethod_replace_audio_placeholders
( content: str, lengths: List[int], n_vq: int, gen_slot_token: str, de
moss_tts_delay/processing_moss_tts.py:454
↓ 1 callersMethod_replace_audio_placeholders
( content: str, lengths: list[int], slot_token: str, audio_start_token: str,
moss_tts_local_v1.5/processing_moss_tts.py:619
↓ 1 callersFunction_resampled_audio_cache_path
(src: Path, target_sample_rate: int)
moss_tts_realtime/fast_api.py:208
↓ 1 callersMethod_reset_parameters
(self)
moss_tts_local_v1.5/gpt2_decoder.py:440
↓ 1 callersMethod_reset_parameters
(self)
moss_tts_local_v1.5/qwen3_decoder.py:413
↓ 1 callersFunction_resolve_dtype
(dtype: str | torch.dtype)
moss_tts_local_v1.5/streaming.py:92
↓ 1 callersFunction_resolve_dtype
(dtype_name: str)
moss_tts_local_v1.5/finetuning/sft.py:264
↓ 1 callersFunction_resolve_dtype
(dtype_name: str)
moss_tts_local_v1.5/finetuning/prepare_data.py:83
↓ 1 callersFunction_resolve_flash_attn
Map flash_attn config value to llama_flash_attn_type int.
moss_tts_delay/llama_cpp/backbone.py:103
↓ 1 callersMethod_resolve_heads_backend
(setting: str)
moss_tts_delay/llama_cpp/pipeline.py:412
↓ 1 callersFunction_resolve_local_dir
Return a local dir for ``path_or_repo_id``. If it's already a local directory, return it unchanged. Otherwise treat it as a HuggingFace Hub r
moss_soundeffect_v2/hf_export.py:84
↓ 1 callersMethod_resolve_local_dir
( pretrained_model_name_or_path: Union[str, os.PathLike], kwargs: dict, )
moss_soundeffect_v2/pipeline_moss_soundeffect.py:138
↓ 1 callersFunction_resolve_overwrite_choice
(save_path: Path, overwrite: bool)
scripts/fuse_moss_tts_delay_with_codec.py:788
↓ 1 callersFunction_resolve_reference_audio_path
(language: str, index: int)
clis/moss_tts_app.py:80
↓ 1 callersFunction_resolve_reference_audio_path
(language: str, index: int)
clis/moss_tts_local_v1.5_app.py:105
↓ 1 callersMethod_resolve_reference_codes
(self, record: Dict[str, Any], target_n_vq: int)
moss_tts_local/finetuning/dataset.py:107
↓ 1 callersMethod_resolve_reference_codes
(self, record: Dict[str, Any], target_n_vq: int)
moss_tts_delay/finetuning/dataset.py:107
↓ 1 callersMethod_resolve_reference_codes
( self, record: Dict[str, Any], target_n_vq: int, )
moss_tts_local_v1.5/finetuning/dataset.py:115
↓ 1 callersFunction_restore_spans
(text: str, protected: list[str])
moss_tts_delay/tts_robust_normalizer_single_script.py:157
↓ 1 callersFunction_sample_next_token_topk_subspace
( *, model: Any, logits: torch.Tensor, do_sample: bool, temperature: float, top_k: Opt
moss_tts_local_v1.5/streaming.py:282
↓ 1 callersFunction_sanitize_audio_tokens
Trim rows after EOS/invalid tokens and return whether decoding should stop.
moss_tts_realtime/mossttsrealtime/streaming_mossttsrealtime.py:906
↓ 1 callersFunction_sanitize_tokens
( tokens: torch.Tensor, codebook_size: int, audio_eos_token: int, )
moss_tts_realtime/example_multiturn_stream_to_tts.py:43
↓ 1 callersFunction_sanitize_tokens
( tokens: torch.Tensor, codebook_size: int, audio_eos_token: int, )
moss_tts_realtime/app.py:301
↓ 1 callersFunction_sanitize_tokens
( tokens: torch.Tensor, codebook_size: int, audio_eos_token: int, )
moss_tts_realtime/fast_api.py:172
↓ 1 callersFunction_sanitize_tokens
( tokens: torch.Tensor, codebook_size: int, audio_eos_token: int, )
moss_tts_realtime/example_llm_stream_to_tts.py:43
↓ 1 callersFunction_save_waveform
(path: Path, waveform: torch.Tensor, sample_rate: int)
moss_tts_local_v1.5/streaming.py:730
↓ 1 callersMethod_sdpa_attention
( self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, a
moss_tts_local_v1.5/gpt2_decoder.py:197
↓ 1 callersMethod_sdpa_attention
( self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, a
moss_tts_local_v1.5/qwen3_decoder.py:191
↓ 1 callersMethod_shard_paths
(self, shard_id: int)
moss_soundeffect_v2/diffsynth/trainers/cache_shards.py:104
↓ 1 callersFunction_smooth_decode_budget_from_lead
(lead_seconds: float)
moss_tts_local_v1.5/streaming.py:707
↓ 1 callersMethod_start_worker
(self, sess: SessionRuntime)
moss_tts_realtime/fast_api.py:542
↓ 1 callersFunction_sync
()
moss_tts_delay/llama_cpp/gpu_monitor.py:101
↓ 1 callersMethod_to_numpy_inputs
(sample: Dict[str, Any])
moss_soundeffect_v2/diffsynth/trainers/cache_shards.py:112
↓ 1 callersFunction_torch_allocated_mb
()
moss_tts_delay/llama_cpp/gpu_monitor.py:111
↓ 1 callersFunction_training_loop
( accelerator: Accelerator, args: argparse.Namespace, model: MossTTSRealtime, train_dataloader
moss_tts_realtime/finetuning/sft.py:562
↓ 1 callersFunction_training_loop
( accelerator: Accelerator, args: argparse.Namespace, model: MossTTSDelayModel, train_dataload
moss_tts_local/finetuning/sft.py:620
↓ 1 callersFunction_training_loop
( accelerator: Accelerator, args: argparse.Namespace, model: MossTTSDelayModel, train_dataload
moss_tts_delay/finetuning/sft.py:617
↓ 1 callersMethod_try_build_direct_codes
( self, conversation: list[Dict[str, Any]], mode: str, n_vq: int, )
moss_tts_local_v1.5/processing_moss_tts.py:467
↓ 1 callersMethod_validate_code_list
( self, codes_list: Optional[List[Optional[torch.Tensor]]], target_n_vq: int,
moss_tts_local/finetuning/dataset.py:90
↓ 1 callersMethod_validate_code_list
( self, codes_list: Optional[List[Optional[torch.Tensor]]], target_n_vq: int,
moss_tts_delay/finetuning/dataset.py:90
↓ 1 callersMethod_validate_paths
( self, prompt_audio: Optional[str], user_audio: Optional[str], use_default_pr
moss_tts_realtime/fast_api.py:340
← previousnext →401–500 of 1,298, ranked by callers