Home / OpenMOSS / MOSS-TTS
Repository Analysis

OpenMOSS/MOSS-TTS

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.

17.9 Moderate AI signal View on GitHub
17.9
Adjusted Score
17.9
Raw Score
100%
Time Factor
2026-05-29
Last Push
2,635
Stars
Python
Language
35,540
Lines of Code
127
Files
383
Pattern Hits
2026-05-31
Scan Date

Score History

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

CRITICAL 0HIGH 19MEDIUM 60LOW 304

Pattern Findings

383 matches across 9 categories. Click a row to expand file-level details.

Decorative Section Separators58 hits · 201 pts
SeverityFileLineSnippet
MEDIUMmoss_tts_realtime/example_multiturn_stream_to_tts.py114# ── Core streaming Generation ──────────────────────────────────────────────────
MEDIUMmoss_tts_realtime/finetuning/dataset.py86 # ------------------------------------------------------------------
MEDIUMmoss_tts_realtime/finetuning/dataset.py88 # ------------------------------------------------------------------
MEDIUMmoss_tts_realtime/finetuning/dataset.py109 # ------------------------------------------------------------------
MEDIUMmoss_tts_realtime/finetuning/dataset.py111 # ------------------------------------------------------------------
MEDIUMmoss_tts_realtime/finetuning/dataset.py166 # ------------------------------------------------------------------
MEDIUMmoss_tts_realtime/finetuning/dataset.py168 # ------------------------------------------------------------------
MEDIUMmoss_tts_realtime/finetuning/dataset.py210 # ------------------------------------------------------------------
MEDIUMmoss_tts_realtime/finetuning/dataset.py212 # ------------------------------------------------------------------
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py44# ---------------------------
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py46# ---------------------------
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py81# ---------------------------
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py83# ---------------------------
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py100# ---------------------------
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py102# ---------------------------
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py246# ---------------------------
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py248# ---------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py51# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py53# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py91# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py93# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py203# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py205# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py349# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py351# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py409 # ── Component factories ──────────────────────────────────────────────
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py471 # ── Generation ───────────────────────────────────────────────────────
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py861# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py863# ---------------------------------------------------------------------------
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py34# ── Name mapping: MossTTSDelay → Qwen3ForCausalLM ──────────────────────────
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py50# ── Helpers ─────────────────────────────────────────────────────────────────
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py86# ── Main extraction ─────────────────────────────────────────────────────────
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py117 # ── Pass: iterate shards and extract all three groups ───────────────
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py150 # ── Embeddings → npy ────────────────────────────────
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py162 # ── LM heads → npy ──────────────────────────────────
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py172 # ── Backbone → Qwen3ForCausalLM safetensors ─────────
MEDIUMconfigs/llama_cpp/trt.yaml19# ── Model paths ──────────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt.yaml26# ── Audio tokenizer ──────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt.yaml32# ── LM heads backend ────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt.yaml36# ── Runtime settings ─────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt.yaml45# ── Sampling parameters ──────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt-8gb.yaml17# ── Model paths ──────────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt-8gb.yaml24# ── Audio tokenizer ──────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt-8gb.yaml31# ── LM heads backend ────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt-8gb.yaml36# ── Runtime settings ─────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt-8gb.yaml49# ── KV cache / attention ────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/trt-8gb.yaml59# ── Sampling parameters ──────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/cpu-only.yaml10# ── Model paths ──────────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/cpu-only.yaml17# ── Audio tokenizer ──────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/cpu-only.yaml23# ── LM heads backend ────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/cpu-only.yaml27# ── Runtime settings ─────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/cpu-only.yaml36# ── Sampling parameters ──────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/default.yaml14# ── Model paths ──────────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/default.yaml26# ── Audio tokenizer ──────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/default.yaml34# ── LM heads backend ────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/default.yaml41# ── Runtime settings ─────────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/default.yaml50# ── KV cache / attention ────────────────────────────────────────────────────
MEDIUMconfigs/llama_cpp/default.yaml61# ── Sampling parameters ──────────────────────────────────────────────────────
Cross-Language Confusion16 hits · 108 pts
SeverityFileLineSnippet
HIGHmoss_tts_realtime/app.py967let audioCtx = null;
HIGHmoss_tts_realtime/app.py971let boundField = null;
HIGHmoss_tts_realtime/app.py977 if (audioCtx && audioCtx.sampleRate !== sr) {
HIGHmoss_tts_realtime/app.py979 audioCtx = null;
HIGHmoss_tts_realtime/app.py982 audioCtx = new (window.AudioContext || window.webkitAudioContext)({ sampleRate: sr });
HIGHmoss_tts_realtime/app.py1048 audioCtx = null;
HIGHmoss_tts_realtime/app.py1055 const sr = payload.sr || 24000;
HIGHmoss_tts_realtime/app.py1061 if (!field || field === boundField) return;
HIGHmoss_tts_realtime/app.py1079 if (v && v !== lastValue) {
HIGHmoss_tts_realtime/app.py1087 if (initial && initial !== lastValue) {
HIGHmoss_tts_realtime/app.py1096 boundField = null;
HIGHmoss_tts_realtime/app.py1118 if (value && value !== lastValue) {
HIGHmoss_tts_realtime/app.py1127 audioCtx = new (window.AudioContext || window.webkitAudioContext)();
HIGHmoss_tts_realtime/finetuning/common.py115 raise ValueError(f"`{field_name}` must be a string, null, or a list containing strings/nulls.")
HIGHmoss_tts_delay/finetuning/common.py115 raise ValueError(f"`{field_name}` must be a string, null, or a list containing strings/nulls.")
HIGHmoss_tts_local/finetuning/common.py115 raise ValueError(f"`{field_name}` must be a string, null, or a list containing strings/nulls.")
Hyper-Verbose Identifiers95 hits · 97 pts
SeverityFileLineSnippet
LOWREADME.md305def resolve_attn_implementation() -> str:
LOWREADME_zh.md312def resolve_attn_implementation() -> str:
LOWmoss_tts_realtime/inferencer.py93 def _build_local_past_key_values(self):
LOWmoss_tts_realtime/inferencer.py354 def generate_local_transformer(
LOWmoss_tts_realtime/fast_api.py208def _resampled_audio_cache_path(src: Path, target_sample_rate: int) -> Path:
LOWmoss_tts_realtime/fast_api.py216def _ensure_audio_resampled_file(src: Path, target_sample_rate: int = SAMPLE_RATE) -> Path:
LOWmoss_tts_realtime/fast_api.py597 def _reset_audio_queue_for_new_turn(self, sess: SessionRuntime) -> None:
LOWmoss_tts_realtime/app.py386def _format_completion_status(
LOWmoss_tts_realtime/app.py519 def _build_text_only_turn_input(
LOWmoss_tts_realtime/infer.py19 def resolve_attn_implementation() -> str:
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py96 def _build_local_past_key_values(self):
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py101 def _get_local_transformer_runner(self):
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py331 def generate_local_transformer(
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py356 def _generate_local_transformer_impl(
LOWmoss_tts_realtime/finetuning/prepare_data.py203def attach_reference_audio_codes(
LOWmoss_tts_realtime/finetuning/common.py103def normalize_audio_path_list(
LOWmoss_tts_realtime/finetuning/sft.py151def resolve_attn_implementation(requested: str, dtype: torch.dtype) -> str:
LOWdocs/moss_tts_realtime_model_card.md107def resolve_attn_implementation() -> str:
LOWdocs/moss_sound_effect_model_card.md67def resolve_attn_implementation() -> str:
LOWdocs/moss_tts_model_card.md129def resolve_attn_implementation() -> str:
LOWdocs/moss_tts_model_card.md248def resolve_attn_implementation() -> str:
LOWdocs/moss_voice_generator_model_card.md50def resolve_attn_implementation() -> str:
LOWdocs/moss_ttsd_model_card.md83def resolve_attn_implementation() -> str:
LOWmoss_tts_delay/processing_moss_tts.py454 def _replace_audio_placeholders(
LOWmoss_tts_delay/processing_moss_tts.py494 def _merge_consecutive_audio_placeholders(
LOWmoss_tts_delay/processing_moss_tts.py770 def _get_audio_tokenizer_device(self) -> torch.device:
LOWmoss_tts_delay/modeling_moss_tts.py199 def _compute_input_embeddings(self, input_ids: torch.LongTensor) -> torch.Tensor:
LOWmoss_tts_delay/tts_robust_normalizer_single_script.py116def _normalize_markdown_and_lines(text: str) -> str:
LOWmoss_tts_delay/tts_robust_normalizer_single_script.py192def _normalize_structural_punctuation(text: str) -> str:
LOWmoss_tts_delay/tts_robust_normalizer_single_script.py223def _normalize_repeated_punctuation(text: str) -> str:
LOWmoss_tts_delay/inference_utils.py62def apply_repetition_penalty_delay_pattern(
LOWmoss_tts_delay/finetuning/prepare_data.py129def attach_reference_audio_codes(
LOWmoss_tts_delay/finetuning/README.md305def resolve_attn_implementation(device: str, dtype: torch.dtype) -> str:
LOWmoss_tts_delay/finetuning/dataset.py32def normalize_audio_code_list(
LOWmoss_tts_delay/finetuning/common.py103def normalize_audio_path_list(
LOWmoss_tts_delay/finetuning/README_zh.md305def resolve_attn_implementation(device: str, dtype: torch.dtype) -> str:
LOWmoss_tts_delay/finetuning/sft.py164def resolve_attn_implementation(requested: str, dtype: torch.dtype) -> str:
LOWmoss_tts_delay/finetuning/sft.py195def parse_channelwise_loss_weight(spec: Optional[str], n_heads: int) -> Optional[List[float]]:
LOWmoss_tts_delay/finetuning/sft.py245def processor_needs_audio_tokenizer(records: List[Dict[str, Any]]) -> bool:
LOWmoss_tts_delay/llama_cpp/gpu_monitor.py85def _nvidia_smi_device_used_mb() -> float:
LOWmoss_tts_delay/llama_cpp/processor.py138def _replace_audio_placeholders(
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py37def _resolve_wan_audio_dit_preset(dit_variant: str):
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py100def _convert_hf_dit_state_dict(state_dict: dict) -> dict:
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py181 def check_resize_num_channels_num_samples(self, num_channels, num_samples):
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py42 def check_resize_height_width(self, height, width, num_frames=None):
LOW…ect_v2/diffsynth/models/wan_video_camera_controller.py46 def process_camera_coordinates(
LOW…ect_v2/diffsynth/models/wan_video_camera_controller.py184def generate_camera_coordinates(
LOWmoss_soundeffect_v2/diffsynth/models/utils.py55def load_state_dict_from_folder(file_path, torch_dtype=None):
LOWmoss_soundeffect_v2/diffsynth/models/utils.py72def load_state_dict_from_safetensors(file_path, torch_dtype=None, device="cpu"):
LOWmoss_soundeffect_v2/diffsynth/models/utils.py148def convert_state_dict_keys_to_single_str(state_dict, with_shape=True):
LOWmoss_soundeffect_v2/diffsynth/models/utils.py164def split_state_dict_with_prefix(state_dict):
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py762 def export_trainable_state_dict(self, state_dict, remove_prefix=None):
LOWscripts/fuse_moss_tts_delay_with_codec.py126def load_added_token_content_by_id(tokenizer_json_path: Path) -> dict[int, str]:
LOWscripts/fuse_moss_tts_delay_with_codec.py157def resolve_processor_token_strings(
LOWscripts/fuse_moss_tts_delay_with_codec.py213def group_weight_map_by_shard(weight_map: dict[str, str]) -> dict[str, list[str]]:
LOWscripts/fuse_moss_tts_delay_with_codec.py222def build_prefixed_codec_keys(
LOWscripts/fuse_moss_tts_delay_with_codec.py247def build_remapped_main_weight_map(main_weight_map: dict[str, str]) -> dict[str, str]:
LOWscripts/fuse_moss_tts_delay_with_codec.py493def collect_tokenizer_asset_filenames(model_dir: Path) -> list[str]:
LOWscripts/fuse_moss_tts_delay_with_codec.py536def local_processor_source_path() -> Path:
LOWscripts/fuse_moss_tts_delay_with_codec.py599def patch_tokenizer_config_processor_class(
35 more matches not shown…
Unused Imports88 hits · 88 pts
SeverityFileLineSnippet
LOWmoss_tts_realtime/example_llm_stream_to_tts.py1
LOWmoss_tts_realtime/infer.py4
LOWmoss_tts_realtime/example_multiturn_stream_to_tts.py1
LOW…realtime/mossttsrealtime/processing_mossttsrealtime.py16
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py16
LOW…s_realtime/mossttsrealtime/modeling_mossttsrealtime.py16
LOWmoss_tts_realtime/mossttsrealtime/__init__.py22
LOWmoss_tts_realtime/mossttsrealtime/__init__.py23
LOWmoss_tts_realtime/mossttsrealtime/__init__.py24
LOWmoss_tts_realtime/mossttsrealtime/__init__.py25
LOWmoss_tts_realtime/mossttsrealtime/__init__.py26
LOW…ltime/mossttsrealtime/configuration_mossttsrealtime.py17
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py16
LOWmoss_tts_realtime/finetuning/dataset.py31
LOWmoss_tts_realtime/finetuning/dataset.py31
LOWmoss_tts_realtime/finetuning/dataset.py31
LOWmoss_tts_realtime/finetuning/dataset.py31
LOWmoss_tts_realtime/finetuning/sft.py40
LOWmoss_tts_delay/processing_moss_tts.py17
LOWmoss_tts_delay/processing_moss_tts.py17
LOWmoss_tts_delay/processing_moss_tts.py17
LOWmoss_tts_delay/tts_robust_normalizer_single_script.py38
LOWmoss_tts_delay/llama_cpp/_constants.py10
LOWmoss_tts_delay/llama_cpp/delay_state.py14
LOWmoss_tts_delay/llama_cpp/delay_state.py21
LOWmoss_tts_delay/llama_cpp/delay_state.py21
LOWmoss_tts_delay/llama_cpp/embedding.py14
LOWmoss_tts_delay/llama_cpp/backbone.py9
LOWmoss_tts_delay/llama_cpp/gpu_monitor.py27
LOWmoss_tts_delay/llama_cpp/__init__.py25
LOWmoss_tts_delay/llama_cpp/__init__.py25
LOWmoss_tts_delay/llama_cpp/processor.py11
LOWmoss_tts_delay/llama_cpp/processor.py30
LOWmoss_tts_delay/llama_cpp/lm_heads.py12
LOWmoss_tts_delay/llama_cpp/pipeline.py25
LOWmoss_tts_delay/llama_cpp/sampling.py8
LOWmoss_tts_delay/llama_cpp/conversion/extract_weights.py20
LOWmoss_soundeffect_v2/__init__.py1
LOWmoss_soundeffect_v2/__init__.py1
LOWmoss_soundeffect_v2/hf_export.py5
LOWmoss_soundeffect_v2/diffsynth/__init__.py1
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py1
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py1
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py1
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py1
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py3
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py4
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py5
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py6
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py7
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py9
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py16
LOWmoss_soundeffect_v2/diffsynth/pipelines/__init__.py1
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py1
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py1
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py5
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py5
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py6
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py9
LOWmoss_soundeffect_v2/diffsynth/models/wan_audio_dit.py3
28 more matches not shown…
Deep Nesting49 hits · 48 pts
SeverityFileLineSnippet
LOWmoss_tts_realtime/fast_api.py552
LOWmoss_tts_realtime/fast_api.py622
LOWmoss_tts_realtime/app.py1146
LOWmoss_tts_realtime/tts_client.py42
LOW…realtime/mossttsrealtime/processing_mossttsrealtime.py90
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py652
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py286
LOWmoss_tts_realtime/finetuning/sft.py562
LOWmoss_tts_delay/processing_moss_tts.py65
LOWmoss_tts_delay/processing_moss_tts.py249
LOWmoss_tts_delay/processing_moss_tts.py688
LOWmoss_tts_delay/processing_moss_tts_delay_with_codec.py74
LOWmoss_tts_delay/finetuning/sft.py617
LOWmoss_tts_delay/llama_cpp/pipeline.py307
LOWmoss_tts_delay/llama_cpp/conversion/extract_weights.py88
LOWmoss_soundeffect_v2/hf_export.py61
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py100
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py685
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py93
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py184
LOWmoss_soundeffect_v2/diffsynth/models/wan_audio_dit.py208
LOWmoss_soundeffect_v2/diffsynth/models/wan_audio_dit.py349
LOWmoss_soundeffect_v2/diffsynth/models/dac_vae.py111
LOWmoss_soundeffect_v2/diffsynth/models/utils.py101
LOWmoss_soundeffect_v2/diffsynth/models/utils.py113
LOWmoss_soundeffect_v2/diffsynth/models/utils.py135
LOWmoss_soundeffect_v2/diffsynth/models/utils.py148
LOWmoss_soundeffect_v2/diffsynth/models/wan_video_dit.py36
LOWmoss_soundeffect_v2/diffsynth/models/wan_video_dit.py387
LOWmoss_soundeffect_v2/diffsynth/models/wan_video_dit.py528
LOWmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py82
LOWmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py124
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py843
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py17
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py325
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py485
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py579
LOWscripts/extract_weights_llama_cpp.py78
LOWscripts/fuse_moss_tts_delay_with_codec.py363
LOWclis/moss_tts_app.py414
LOWclis/moss_ttsd_app.py72
LOWclis/moss_ttsd_app.py530
LOWclis/moss_voice_generator_app.py210
LOWclis/moss_sound_effect_app.py85
LOWmoss_tts_local/processing_moss_tts.py64
LOWmoss_tts_local/processing_moss_tts.py250
LOWmoss_tts_local/processing_moss_tts.py688
LOWmoss_tts_local/finetuning/sft.py620
LOWcommunity/norwegian-lora/train_lora.py416
Excessive Try-Catch Wrapping40 hits · 44 pts
SeverityFileLineSnippet
LOWmoss_tts_realtime/fast_api.py32except Exception:
LOWmoss_tts_realtime/fast_api.py221 except Exception:
LOWmoss_tts_realtime/fast_api.py420 except Exception as e:
LOWmoss_tts_realtime/fast_api.py560 except Exception as e:
LOWmoss_tts_realtime/fast_api.py580 except Exception as e:
LOWmoss_tts_realtime/fast_api.py588 except Exception:
LOWmoss_tts_realtime/fast_api.py594 except Exception:
LOWmoss_tts_realtime/fast_api.py713 except Exception:
LOWmoss_tts_realtime/fast_api.py719 except Exception:
LOWmoss_tts_realtime/fast_api.py841 except Exception:
LOWmoss_tts_realtime/fast_api.py920 except Exception as e:
LOWmoss_tts_realtime/fast_api.py947 except Exception as e:
LOWmoss_tts_realtime/fast_api.py987 except Exception:
LOWmoss_tts_realtime/app.py832 except Exception as exc:
LOWmoss_tts_realtime/app.py1296 except Exception as exc:
MEDIUMmoss_tts_realtime/app.py731def _run(self) -> None:
LOWmoss_tts_realtime/tts_client.py89 except Exception as exc:
LOWmoss_tts_realtime/tts_client.py195 except Exception as e:
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py811 except Exception:
LOWmoss_tts_delay/processing_moss_tts.py215 except Exception:
LOWmoss_tts_delay/processing_moss_tts.py311 except Exception:
LOWmoss_tts_delay/modeling_moss_tts.py42except Exception:
LOWmoss_tts_delay/llama_cpp/_constants.py44 except Exception as exc:
LOWmoss_tts_delay/llama_cpp/gpu_monitor.py57 except Exception:
LOWmoss_tts_delay/llama_cpp/gpu_monitor.py96 except Exception:
LOWmoss_tts_delay/llama_cpp/pipeline.py617 except Exception:
LOWmoss_tts_delay/llama_cpp/pipeline.py761 except Exception as e:
LOWmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py23 except Exception:
LOWmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py221 except Exception:
MEDIUMmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py18def _get_rank_and_world_size() -> Tuple[int, int]:
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py505 except Exception:
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py570 except Exception:
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py613 except Exception:
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py662 except Exception as e:
LOWscripts/fuse_moss_tts_delay_with_codec.py475 except Exception as exc:
LOWscripts/batch_eval_llama_cpp.py165 except Exception as e:
LOWmoss_tts_local/processing_moss_tts.py214 except Exception:
LOWmoss_tts_local/processing_moss_tts.py312 except Exception:
LOWcommunity/norwegian-lora/train_lora.py106 except Exception as exc:
LOWcommunity/norwegian-lora/train_lora.py121 except Exception as exc:
Over-Commented Block33 hits · 33 pts
SeverityFileLineSnippet
LOW…realtime/mossttsrealtime/processing_mossttsrealtime.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py1# Copyright 2025 The HuggingFace Team. All rights reserved.
LOW…s_realtime/mossttsrealtime/modeling_mossttsrealtime.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.
LOWmoss_tts_realtime/mossttsrealtime/__init__.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.
LOW…ltime/mossttsrealtime/configuration_mossttsrealtime.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.
LOWmoss_tts_realtime/finetuning/prepare_data.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_realtime/finetuning/dataset.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_realtime/finetuning/common.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_realtime/finetuning/sft.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_delay/processing_moss_tts.py1# coding=utf-8
LOWmoss_tts_delay/modeling_moss_tts.py1# coding=utf-8
LOWmoss_tts_delay/configuration_moss_tts.py1# coding=utf-8
LOWmoss_tts_delay/inference_utils.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_delay/finetuning/prepare_data.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_delay/finetuning/dataset.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_delay/finetuning/common.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_delay/finetuning/sft.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_delay/llama_cpp/build_bridge.sh1#!/usr/bin/env bash
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py141 # WanVideoUnit_ImageEmbedderVAE(),
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py281
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py301 # camera_control_speed: Optional[float] = 1/54,
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py321 switch_DiT_boundary: Optional[float] = 0.875,
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py361 # "input_video": input_video, "denoising_strength": denoising_strength,
LOWconfigs/llama_cpp/trt.yaml1# MOSS-TTS-Delay — llama.cpp Backend (TensorRT audio, maximum performance)
LOWconfigs/llama_cpp/trt-8gb.yaml1# MOSS-TTS-Delay — 8 GB GPU config (low-memory mode)
LOWconfigs/llama_cpp/default.yaml1# MOSS-TTS-Delay — llama.cpp Backend (ONNX audio, default)
LOWmoss_tts_local/processing_moss_tts.py1# coding=utf-8
LOWmoss_tts_local/configuration_moss_tts.py1# coding=utf-8
LOWmoss_tts_local/finetuning/prepare_data.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_local/finetuning/dataset.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_local/finetuning/common.py1# Copyright 2026 OpenMOSS team. All rights reserved.
LOWmoss_tts_local/finetuning/sft.py1# Copyright 2026 OpenMOSS team. All rights reserved.
Cross-File Repetition3 hits · 15 pts
SeverityFileLineSnippet
HIGH…ect_v2/diffsynth/models/wan_video_camera_controller.py0copied from https://github.com/hehao13/cameractrl/blob/main/inference.py
HIGH…ect_v2/diffsynth/models/wan_video_camera_controller.py0copied from https://github.com/hehao13/cameractrl/blob/main/inference.py
HIGH…ect_v2/diffsynth/models/wan_video_camera_controller.py0copied from https://github.com/hehao13/cameractrl/blob/main/inference.py
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippet
LOWmoss_tts_delay/llama_cpp/build_bridge.sh4# Usage: