Home / OpenMOSS / MOSS-TTS
AI Slop Code RIsk Monitor

OpenMOSS/MOSS-TTS

An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

26.5 Elevated pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for OpenMOSS/MOSS-TTS, a Python project with 4,193 GitHub stars. SynthScan examined 44,616 lines of code across 147 source files, recording 635 pattern matches distributed across 13 syntactic categories. The legacy adjusted pattern signal is 26.5 (Elevated pattern signal); it is not an authorship estimate.

Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.

26.5
Adjusted Signal
26.5
Raw Pattern Score
100%
Time Factor
2026-09-06
Last Push
4.2K
Stars
Python
Language
44.6K
Lines of Code
147
Files
635
Pattern Hits
2026-10-12
Scan Date
0.69
HC Hit Rate

Risk Review · v3

Use each vector to guide manual verification of the underlying findings.

Cognitive Ownership Risk 28.8/100 · MEDIUM

Can maintainers explain intent, assumptions, and trade-offs? 300 finding(s).

Hallucinated Dependency & Supply Chain Risk 44.3/100 · MEDIUM

Are imports declared and package/API names verified? 188 finding(s).

Agent Over-Engineering Ratio 46.5/100 · MEDIUM

Are wrappers, guards, and repeated structures necessary? 344 finding(s).

PR Review Velocity Impact 75.8/100 · CRITICAL

Which changes need focused human review? 635 finding(s).

What These Metrics Mean

Adjusted Signal
Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score
Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor
A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits
Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate
High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files
Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 0HIGH 102MEDIUM 61LOW 472

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 635 distinct pattern matches across 13 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Cross-Language Confusion84 hits · 419 pts
SeverityFileLineSnippetContext
HIGH⚡moss_tts_realtime/app.py967let audioCtx = null;CODE
HIGH⚡moss_tts_realtime/app.py971let boundField = null;CODE
HIGH⚡moss_tts_realtime/app.py977 if (audioCtx && audioCtx.sampleRate !== sr) {CODE
HIGH⚡moss_tts_realtime/app.py979 audioCtx = null;CODE
HIGH⚡moss_tts_realtime/app.py982 audioCtx = new (window.AudioContext || window.webkitAudioContext)({ sampleRate: sr });CODE
HIGH⚡moss_tts_realtime/app.py1048 audioCtx = null;CODE
HIGH⚡moss_tts_realtime/app.py1055 const sr = payload.sr || 24000;CODE
HIGH⚡moss_tts_realtime/app.py1061 if (!field || field === boundField) return;CODE
HIGH⚡moss_tts_realtime/app.py1079 if (v && v !== lastValue) {CODE
HIGH⚡moss_tts_realtime/app.py1087 if (initial && initial !== lastValue) {CODE
HIGH⚡moss_tts_realtime/app.py1096 boundField = null;CODE
HIGHmoss_tts_realtime/app.py1118 if (value && value !== lastValue) {CODE
HIGHmoss_tts_realtime/app.py1127 audioCtx = new (window.AudioContext || window.webkitAudioContext)();CODE
HIGHmoss_tts_realtime/finetuning/common.py115 raise ValueError(f"`{field_name}` must be a string, null, or a list containing strings/nulls.")CODE
HIGHmoss_tts_delay/finetuning/common.py115 raise ValueError(f"`{field_name}` must be a string, null, or a list containing strings/nulls.")CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1063let currentJob = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1064let audioContext = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1066let statusTimer = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1069let currentStreamAbortController = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1072let playbackCompletionTimer = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1078let currentReferenceObjectUrl = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1080let recordedReferenceFile = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1082let referenceRecordingStream = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1083let referenceRecordingAudioContext = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1084let referenceRecordingSource = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1085let referenceRecordingProcessor = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1089let referenceRecordingTimer = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1113 return Boolean(field("prompt-audio").files[0] || recordedReferenceFile || field("example-audio-path").value);CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1116 field("status").textContent = typeof obj === "string" ? obj : JSON.stringify(obj, null, 2);CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1117 if (obj && (obj.generated_frames || obj.generated_frames === 0) && obj.max_new_tokens) {CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1118 const pct = Math.min(100, 100 * Number(obj.generated_frames || 0) / Number(obj.max_new_tokens || 1));CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1130 runtimeReady = status && status.state === "ready";CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1131 const elapsed = status && status.load_elapsed_seconds != null ? ` | load=${Number(status.load_elapsed_seconds).toFixedCODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1133 const error = status && status.error ? ` | error=${status.error}` : "";CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1134 field("runtime-summary").textContent = `Runtime: ${(status && status.state) || "unknown"}${elapsed}${extra}${error}`;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1162 currentReferenceObjectUrl = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1172function showReferencePreview(src, objectUrl = null) {CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1175 currentReferenceObjectUrl = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1215 if (referenceRecordingActive && nextMode !== "record") stopReferenceRecording(true);CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1218 recordedReferenceFile = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1228 const safeSeconds = Math.max(0, Math.floor(seconds || 0));CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1285 referenceRecordingTimer = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1289 referenceRecordingProcessor.onaudioprocess = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1290 referenceRecordingProcessor = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1294 referenceRecordingSource = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1298 referenceRecordingStream = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1302 referenceRecordingAudioContext = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1311 recordedReferenceFile = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1315 const AudioContextCtor = window.AudioContext || window.webkitAudioContext;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1318 referenceRecordingSampleRate = referenceRecordingAudioContext.sampleRate || 48000;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1326 referenceRecordingChunks.push(new Float32Array(input));CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1506 const raw = Number(field("initial-playback-delay").value || 0.08);CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1519 const bytesPerFrame = Math.max(1, Number(channels || 2) * 2);CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1521 const resolvedSampleRate = Math.max(1, Number(sampleRate || 48000));CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1592 statusTimer = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1596 currentStreamAbortController = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1600 currentJob = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1604 audioContext = null;CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1617 if (playbackPaused || nextPlaybackTime - audioContext.currentTime > 0.05) {CODE
HIGH⚡clis/moss_tts_local_v1.5_app.py1622 audioContext = null;CODE
24 more matches not shown…
Decorative Section Separators58 hits · 201 pts
SeverityFileLineSnippetContext
MEDIUMmoss_tts_realtime/example_multiturn_stream_to_tts.py114# ── Core streaming Generation ──────────────────────────────────────────────────COMMENT
MEDIUMmoss_tts_realtime/finetuning/dataset.py86 # ------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_realtime/finetuning/dataset.py88 # ------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_realtime/finetuning/dataset.py109 # ------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_realtime/finetuning/dataset.py111 # ------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_realtime/finetuning/dataset.py166 # ------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_realtime/finetuning/dataset.py168 # ------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_realtime/finetuning/dataset.py210 # ------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_realtime/finetuning/dataset.py212 # ------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py44# ---------------------------COMMENT
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py46# ---------------------------COMMENT
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py81# ---------------------------COMMENT
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py83# ---------------------------COMMENT
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py100# ---------------------------COMMENT
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py102# ---------------------------COMMENT
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py246# ---------------------------COMMENT
MEDIUMmoss_tts_delay/tts_robust_normalizer_single_script.py248# ---------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py51# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py53# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py91# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py93# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py203# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py205# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py349# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py351# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py409 # ── Component factories ──────────────────────────────────────────────COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py471 # ── Generation ───────────────────────────────────────────────────────COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py861# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/pipeline.py863# ---------------------------------------------------------------------------COMMENT
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py34# ── Name mapping: MossTTSDelay → Qwen3ForCausalLM ──────────────────────────COMMENT
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py50# ── Helpers ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py86# ── Main extraction ─────────────────────────────────────────────────────────COMMENT
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py117 # ── Pass: iterate shards and extract all three groups ───────────────COMMENT
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py150 # ── Embeddings → npy ────────────────────────────────COMMENT
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py162 # ── LM heads → npy ──────────────────────────────────COMMENT
MEDIUMmoss_tts_delay/llama_cpp/conversion/extract_weights.py172 # ── Backbone → Qwen3ForCausalLM safetensors ─────────COMMENT
MEDIUM⚡configs/llama_cpp/trt.yaml19# ── Model paths ──────────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/trt.yaml26# ── Audio tokenizer ──────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/trt.yaml32# ── LM heads backend ────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/trt.yaml36# ── Runtime settings ─────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/trt.yaml45# ── Sampling parameters ──────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/trt-8gb.yaml17# ── Model paths ──────────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/trt-8gb.yaml24# ── Audio tokenizer ──────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/trt-8gb.yaml31# ── LM heads backend ────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/trt-8gb.yaml36# ── Runtime settings ─────────────────────────────────────────────────────────COMMENT
MEDIUMconfigs/llama_cpp/trt-8gb.yaml49# ── KV cache / attention ────────────────────────────────────────────────────COMMENT
MEDIUMconfigs/llama_cpp/trt-8gb.yaml59# ── Sampling parameters ──────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/cpu-only.yaml10# ── Model paths ──────────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/cpu-only.yaml17# ── Audio tokenizer ──────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/cpu-only.yaml23# ── LM heads backend ────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/cpu-only.yaml27# ── Runtime settings ─────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/cpu-only.yaml36# ── Sampling parameters ──────────────────────────────────────────────────────COMMENT
MEDIUMconfigs/llama_cpp/default.yaml14# ── Model paths ──────────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/default.yaml26# ── Audio tokenizer ──────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/default.yaml34# ── LM heads backend ────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/default.yaml41# ── Runtime settings ─────────────────────────────────────────────────────────COMMENT
MEDIUM⚡configs/llama_cpp/default.yaml50# ── KV cache / attention ────────────────────────────────────────────────────COMMENT
MEDIUMconfigs/llama_cpp/default.yaml61# ── Sampling parameters ──────────────────────────────────────────────────────COMMENT
Hyper-Verbose Identifiers153 hits · 157 pts
SeverityFileLineSnippetContext
LOWREADME.md355def resolve_attn_implementation() -> str:CODE
LOWREADME_zh.md362def resolve_attn_implementation() -> str:CODE
LOWmoss_tts_realtime/inferencer.py93 def _build_local_past_key_values(self):CODE
LOWmoss_tts_realtime/inferencer.py354 def generate_local_transformer(CODE
LOW⚡moss_tts_realtime/fast_api.py208def _resampled_audio_cache_path(src: Path, target_sample_rate: int) -> Path:CODE
LOW⚡moss_tts_realtime/fast_api.py216def _ensure_audio_resampled_file(src: Path, target_sample_rate: int = SAMPLE_RATE) -> Path:CODE
LOW⚡moss_tts_realtime/fast_api.py597 def _reset_audio_queue_for_new_turn(self, sess: SessionRuntime) -> None:CODE
LOWmoss_tts_realtime/app.py386def _format_completion_status(CODE
LOWmoss_tts_realtime/app.py519 def _build_text_only_turn_input(CODE
LOWmoss_tts_realtime/infer.py19 def resolve_attn_implementation() -> str:CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py96 def _build_local_past_key_values(self):CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py101 def _get_local_transformer_runner(self):CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py331 def generate_local_transformer(CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py356 def _generate_local_transformer_impl(CODE
LOWmoss_tts_realtime/finetuning/prepare_data.py203def attach_reference_audio_codes(CODE
LOWmoss_tts_realtime/finetuning/common.py103def normalize_audio_path_list(CODE
LOWmoss_tts_realtime/finetuning/sft.py151def resolve_attn_implementation(requested: str, dtype: torch.dtype) -> str:CODE
LOWdocs/moss_tts_realtime_model_card.md107def resolve_attn_implementation() -> str:CODE
LOWdocs/moss_sound_effect_model_card.md67def resolve_attn_implementation() -> str:CODE
LOWdocs/moss_tts_model_card.md131def resolve_attn_implementation() -> str:CODE
LOWdocs/moss_tts_model_card.md250def resolve_attn_implementation() -> str:CODE
LOWdocs/moss_voice_generator_model_card.md50def resolve_attn_implementation() -> str:CODE
LOWdocs/moss_ttsd_model_card.md83def resolve_attn_implementation() -> str:CODE
LOWmoss_tts_delay/processing_moss_tts.py454 def _replace_audio_placeholders(CODE
LOWmoss_tts_delay/processing_moss_tts.py494 def _merge_consecutive_audio_placeholders(CODE
LOWmoss_tts_delay/processing_moss_tts.py770 def _get_audio_tokenizer_device(self) -> torch.device:CODE
LOWmoss_tts_delay/modeling_moss_tts.py199 def _compute_input_embeddings(self, input_ids: torch.LongTensor) -> torch.Tensor:STRING
LOWmoss_tts_delay/tts_robust_normalizer_single_script.py116def _normalize_markdown_and_lines(text: str) -> str:CODE
LOWmoss_tts_delay/tts_robust_normalizer_single_script.py192def _normalize_structural_punctuation(text: str) -> str:CODE
LOWmoss_tts_delay/tts_robust_normalizer_single_script.py223def _normalize_repeated_punctuation(text: str) -> str:CODE
LOWmoss_tts_delay/inference_utils.py62def apply_repetition_penalty_delay_pattern(CODE
LOWmoss_tts_delay/finetuning/prepare_data.py129def attach_reference_audio_codes(CODE
LOWmoss_tts_delay/finetuning/README.md305def resolve_attn_implementation(device: str, dtype: torch.dtype) -> str:CODE
LOWmoss_tts_delay/finetuning/dataset.py32def normalize_audio_code_list(CODE
LOWmoss_tts_delay/finetuning/common.py103def normalize_audio_path_list(CODE
LOWmoss_tts_delay/finetuning/README_zh.md305def resolve_attn_implementation(device: str, dtype: torch.dtype) -> str:CODE
LOWmoss_tts_delay/finetuning/sft.py164def resolve_attn_implementation(requested: str, dtype: torch.dtype) -> str:CODE
LOWmoss_tts_delay/finetuning/sft.py195def parse_channelwise_loss_weight(spec: Optional[str], n_heads: int) -> Optional[List[float]]:CODE
LOWmoss_tts_delay/finetuning/sft.py245def processor_needs_audio_tokenizer(records: List[Dict[str, Any]]) -> bool:CODE
LOWmoss_tts_delay/llama_cpp/gpu_monitor.py85def _nvidia_smi_device_used_mb() -> float:CODE
LOWmoss_tts_delay/llama_cpp/processor.py138def _replace_audio_placeholders(CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py37def _resolve_wan_audio_dit_preset(dit_variant: str):CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py100def _convert_hf_dit_state_dict(state_dict: dict) -> dict:CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py181 def check_resize_num_channels_num_samples(self, num_channels, num_samples):CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py42 def check_resize_height_width(self, height, width, num_frames=None):CODE
LOW…ect_v2/diffsynth/models/wan_video_camera_controller.py46 def process_camera_coordinates(CODE
LOW…ect_v2/diffsynth/models/wan_video_camera_controller.py184def generate_camera_coordinates(CODE
LOWmoss_soundeffect_v2/diffsynth/models/utils.py55def load_state_dict_from_folder(file_path, torch_dtype=None):CODE
LOWmoss_soundeffect_v2/diffsynth/models/utils.py72def load_state_dict_from_safetensors(file_path, torch_dtype=None, device="cpu"):CODE
LOWmoss_soundeffect_v2/diffsynth/models/utils.py148def convert_state_dict_keys_to_single_str(state_dict, with_shape=True):CODE
LOWmoss_soundeffect_v2/diffsynth/models/utils.py164def split_state_dict_with_prefix(state_dict):CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py762 def export_trainable_state_dict(self, state_dict, remove_prefix=None):CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py126def load_added_token_content_by_id(tokenizer_json_path: Path) -> dict[int, str]:CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py157def resolve_processor_token_strings(CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py213def group_weight_map_by_shard(weight_map: dict[str, str]) -> dict[str, list[str]]:CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py222def build_prefixed_codec_keys(CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py247def build_remapped_main_weight_map(main_weight_map: dict[str, str]) -> dict[str, str]:CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py493def collect_tokenizer_asset_filenames(model_dir: Path) -> list[str]:CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py536def local_processor_source_path() -> Path:CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py599def patch_tokenizer_config_processor_class(CODE
93 more matches not shown…
Unused Imports104 hits · 104 pts
SeverityFileLineSnippetContext
LOWmoss_tts_realtime/example_llm_stream_to_tts.py1CODE
LOWmoss_tts_realtime/infer.py4CODE
LOWmoss_tts_realtime/example_multiturn_stream_to_tts.py1CODE
LOW…realtime/mossttsrealtime/processing_mossttsrealtime.py16CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py16CODE
LOW…s_realtime/mossttsrealtime/modeling_mossttsrealtime.py16CODE
LOWmoss_tts_realtime/mossttsrealtime/__init__.py22CODE
LOWmoss_tts_realtime/mossttsrealtime/__init__.py23CODE
LOWmoss_tts_realtime/mossttsrealtime/__init__.py24CODE
LOWmoss_tts_realtime/mossttsrealtime/__init__.py25CODE
LOWmoss_tts_realtime/mossttsrealtime/__init__.py26CODE
LOW…ltime/mossttsrealtime/configuration_mossttsrealtime.py17CODE
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py16CODE
LOWmoss_tts_realtime/finetuning/dataset.py31CODE
LOWmoss_tts_realtime/finetuning/dataset.py31CODE
LOWmoss_tts_realtime/finetuning/dataset.py31CODE
LOWmoss_tts_realtime/finetuning/dataset.py31CODE
LOWmoss_tts_realtime/finetuning/sft.py40CODE
LOWmoss_tts_delay/processing_moss_tts.py17CODE
LOWmoss_tts_delay/processing_moss_tts.py17CODE
LOWmoss_tts_delay/processing_moss_tts.py17CODE
LOWmoss_tts_delay/tts_robust_normalizer_single_script.py38CODE
LOWmoss_tts_delay/llama_cpp/_constants.py10CODE
LOWmoss_tts_delay/llama_cpp/delay_state.py14CODE
LOWmoss_tts_delay/llama_cpp/delay_state.py21CODE
LOWmoss_tts_delay/llama_cpp/delay_state.py21CODE
LOWmoss_tts_delay/llama_cpp/embedding.py14CODE
LOWmoss_tts_delay/llama_cpp/backbone.py9CODE
LOWmoss_tts_delay/llama_cpp/gpu_monitor.py27CODE
LOWmoss_tts_delay/llama_cpp/__init__.py25CODE
LOWmoss_tts_delay/llama_cpp/__init__.py25CODE
LOWmoss_tts_delay/llama_cpp/processor.py11CODE
LOWmoss_tts_delay/llama_cpp/processor.py30CODE
LOWmoss_tts_delay/llama_cpp/lm_heads.py12CODE
LOWmoss_tts_delay/llama_cpp/pipeline.py25CODE
LOWmoss_tts_delay/llama_cpp/sampling.py8CODE
LOWmoss_tts_delay/llama_cpp/conversion/extract_weights.py20CODE
LOWmoss_soundeffect_v2/__init__.py1CODE
LOWmoss_soundeffect_v2/__init__.py1CODE
LOWmoss_soundeffect_v2/hf_export.py5CODE
LOWmoss_soundeffect_v2/diffsynth/__init__.py1CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py1CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py1CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py1CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py1CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py3CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py4CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py5CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py6CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py7CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py9CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py16CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/__init__.py1CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py1CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py1CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py5CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py5CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py6CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py9CODE
LOWmoss_soundeffect_v2/diffsynth/models/wan_audio_dit.py3CODE
44 more matches not shown…
Empty Error Handlers15 hits · 68 pts
SeverityFileLineSnippetContext
HIGHmoss_tts_realtime/fast_api.py588except Exception:CODE
HIGHmoss_tts_realtime/fast_api.py987except Exception:CODE
HIGHmoss_tts_realtime/fast_api.py594except Exception:CODE
HIGHmoss_tts_realtime/fast_api.py713except Exception:CODE
HIGHmoss_tts_realtime/fast_api.py841except Exception:CODE
HIGHmoss_tts_delay/llama_cpp/gpu_monitor.py96except Exception:CODE
HIGHmoss_tts_delay/llama_cpp/gpu_monitor.py107except ImportError:CODE
HIGHmoss_tts_delay/llama_cpp/gpu_monitor.py116except ImportError:CODE
HIGHmoss_tts_delay/llama_cpp/pipeline.py87except ImportError:CODE
HIGHclis/moss_tts_local_v1.5_app.py375except queue.Full:CODE
HIGHclis/moss_tts_local_v1.5_app.py511except queue.Full:CODE
HIGHclis/moss_tts_local_v1.5_app.py517except queue.Full:CODE
HIGHmoss_tts_local_v1.5/streaming.py125except Exception:CODE
HIGHmoss_tts_local_v1.5/finetuning/prepare_data.py111except Exception:CODE
HIGHmoss_tts_local_v1.5/finetuning/sft.py293except Exception:CODE
Deep Nesting63 hits · 60 pts
SeverityFileLineSnippetContext
LOWmoss_tts_realtime/fast_api.py552CODE
LOWmoss_tts_realtime/fast_api.py622CODE
LOWmoss_tts_realtime/app.py1146CODE
LOWmoss_tts_realtime/tts_client.py42CODE
LOW…realtime/mossttsrealtime/processing_mossttsrealtime.py90CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py652CODE
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py286CODE
LOWmoss_tts_realtime/finetuning/sft.py562CODE
LOWmoss_tts_delay/processing_moss_tts.py65CODE
LOWmoss_tts_delay/processing_moss_tts.py249CODE
LOWmoss_tts_delay/processing_moss_tts.py688CODE
LOWmoss_tts_delay/processing_moss_tts_delay_with_codec.py74CODE
LOWmoss_tts_delay/finetuning/sft.py617CODE
LOWmoss_tts_delay/llama_cpp/pipeline.py307CODE
LOWmoss_tts_delay/llama_cpp/conversion/extract_weights.py88CODE
LOWmoss_soundeffect_v2/hf_export.py61CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py100CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py685CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py93CODE
LOWmoss_soundeffect_v2/diffsynth/utils/__init__.py184CODE
LOWmoss_soundeffect_v2/diffsynth/models/wan_audio_dit.py208CODE
LOWmoss_soundeffect_v2/diffsynth/models/wan_audio_dit.py349CODE
LOWmoss_soundeffect_v2/diffsynth/models/dac_vae.py111CODE
LOWmoss_soundeffect_v2/diffsynth/models/utils.py101CODE
LOWmoss_soundeffect_v2/diffsynth/models/utils.py113CODE
LOWmoss_soundeffect_v2/diffsynth/models/utils.py135CODE
LOWmoss_soundeffect_v2/diffsynth/models/utils.py148CODE
LOWmoss_soundeffect_v2/diffsynth/models/wan_video_dit.py36CODE
LOWmoss_soundeffect_v2/diffsynth/models/wan_video_dit.py387CODE
LOWmoss_soundeffect_v2/diffsynth/models/wan_video_dit.py528CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py82CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py124CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py843CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py17CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py325CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py485CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py579CODE
LOWscripts/extract_weights_llama_cpp.py78CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py363CODE
LOWclis/moss_tts_app.py414CODE
LOWclis/moss_ttsd_app.py72CODE
LOWclis/moss_ttsd_app.py530CODE
LOWclis/moss_voice_generator_app.py210CODE
LOWclis/moss_sound_effect_app.py85CODE
LOWclis/moss_tts_local_v1.5_app.py380CODE
LOWclis/moss_tts_local_v1.5_app.py449CODE
LOWmoss_tts_local/processing_moss_tts.py64CODE
LOWmoss_tts_local/processing_moss_tts.py250CODE
LOWmoss_tts_local/processing_moss_tts.py688CODE
LOWmoss_tts_local/finetuning/sft.py620CODE
LOWmoss_tts_local_v1.5/processing_moss_tts.py483CODE
LOWmoss_tts_local_v1.5/processing_moss_tts.py727CODE
LOWmoss_tts_local_v1.5/qwen3_decoder.py467CODE
LOWmoss_tts_local_v1.5/gpt2_decoder.py440CODE
LOWmoss_tts_local_v1.5/gpt2_decoder.py595CODE
LOWmoss_tts_local_v1.5/streaming.py105CODE
LOWmoss_tts_local_v1.5/streaming.py735CODE
LOWmoss_tts_local_v1.5/streaming.py1083CODE
LOWmoss_tts_local_v1.5/streaming.py781CODE
LOWmoss_tts_local_v1.5/finetuning/common.py103CODE
3 more matches not shown…
Excessive Try-Catch Wrapping54 hits · 58 pts
SeverityFileLineSnippetContext
LOW⚡moss_tts_realtime/fast_api.py221 except Exception:CODE
LOW⚡moss_tts_realtime/fast_api.py580 except Exception as e:CODE
LOW⚡moss_tts_realtime/fast_api.py588 except Exception:CODE
LOW⚡moss_tts_realtime/fast_api.py594 except Exception:CODE
LOWmoss_tts_realtime/fast_api.py32except Exception:CODE
LOWmoss_tts_realtime/fast_api.py420 except Exception as e:CODE
LOWmoss_tts_realtime/fast_api.py560 except Exception as e:CODE
LOWmoss_tts_realtime/fast_api.py713 except Exception:CODE
LOWmoss_tts_realtime/fast_api.py719 except Exception:CODE
LOWmoss_tts_realtime/fast_api.py841 except Exception:CODE
LOWmoss_tts_realtime/fast_api.py920 except Exception as e:CODE
LOWmoss_tts_realtime/fast_api.py947 except Exception as e:CODE
LOWmoss_tts_realtime/fast_api.py987 except Exception:CODE
LOWmoss_tts_realtime/app.py832 except Exception as exc:CODE
LOWmoss_tts_realtime/app.py1296 except Exception as exc:STRING
MEDIUMmoss_tts_realtime/app.py731def _run(self) -> None:CODE
LOWmoss_tts_realtime/tts_client.py89 except Exception as exc:CODE
LOWmoss_tts_realtime/tts_client.py195 except Exception as e:CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py811 except Exception:CODE
LOWmoss_tts_delay/processing_moss_tts.py215 except Exception:CODE
LOWmoss_tts_delay/processing_moss_tts.py311 except Exception:CODE
LOWmoss_tts_delay/modeling_moss_tts.py42except Exception:CODE
LOWmoss_tts_delay/llama_cpp/_constants.py44 except Exception as exc:CODE
LOWmoss_tts_delay/llama_cpp/gpu_monitor.py57 except Exception:CODE
LOWmoss_tts_delay/llama_cpp/gpu_monitor.py96 except Exception:CODE
LOWmoss_tts_delay/llama_cpp/pipeline.py617 except Exception:CODE
LOWmoss_tts_delay/llama_cpp/pipeline.py761 except Exception as e:CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py23 except Exception:CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py221 except Exception:CODE
MEDIUMmoss_soundeffect_v2/diffsynth/trainers/cache_shards.py18def _get_rank_and_world_size() -> Tuple[int, int]:CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py505 except Exception:CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py570 except Exception:CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py613 except Exception:CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py662 except Exception as e:CODE
LOWscripts/fuse_moss_tts_delay_with_codec.py475 except Exception as exc:CODE
LOWscripts/batch_eval_llama_cpp.py165 except Exception as e:CODE
MEDIUMclis/moss_tts_local_v1.5_app.py281def _load() -> None:CODE
LOWclis/moss_tts_local_v1.5_app.py284 except Exception:CODE
LOWclis/moss_tts_local_v1.5_app.py307 except Exception as exc:CODE
LOWclis/moss_tts_local_v1.5_app.py513 except Exception as exc: # noqa: BLE001CODE
LOWmoss_tts_local/processing_moss_tts.py214 except Exception:CODE
LOWmoss_tts_local/processing_moss_tts.py312 except Exception:CODE
LOWmoss_tts_local_v1.5/processing_moss_tts.py247 except Exception:CODE
LOWmoss_tts_local_v1.5/processing_moss_tts.py529 except Exception:CODE
LOWmoss_tts_local_v1.5/qwen3_decoder.py22except Exception:CODE
LOWmoss_tts_local_v1.5/gpt2_decoder.py19except Exception:CODE
LOWmoss_tts_local_v1.5/streaming.py125 except Exception:CODE
LOW⚡moss_tts_local_v1.5/streaming.py645 except Exception as exc: # noqa: BLE001CODE
LOW⚡moss_tts_local_v1.5/streaming.py655 except Exception as exc: # noqa: BLE001CODE
LOWmoss_tts_local_v1.5/finetuning/prepare_data.py111 except Exception:CODE
LOWmoss_tts_local_v1.5/finetuning/sft.py36except Exception:CODE
LOWmoss_tts_local_v1.5/finetuning/sft.py293 except Exception:CODE
LOW⚡community/norwegian-lora/train_lora.py106 except Exception as exc:CODE
LOW⚡community/norwegian-lora/train_lora.py121 except Exception as exc:CODE
AI Structural Patterns44 hits · 42 pts
SeverityFileLineSnippetContext
LOWmoss_tts_realtime/inferencer.py306CODE
LOW…realtime/mossttsrealtime/processing_mossttsrealtime.py34CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py153CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py486CODE
LOW…s_realtime/mossttsrealtime/modeling_mossttsrealtime.py111CODE
LOW…ltime/mossttsrealtime/configuration_mossttsrealtime.py38CODE
LOW…ltime/mossttsrealtime/configuration_mossttsrealtime.py88CODE
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py286CODE
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py395CODE
LOWmoss_tts_delay/processing_moss_tts.py375CODE
LOWmoss_tts_delay/processing_moss_tts.py491CODE
LOWmoss_tts_delay/processing_moss_tts_delay_with_codec.py18CODE
LOWmoss_tts_delay/modeling_moss_tts.py226CODE
LOWmoss_tts_delay/modeling_moss_tts.py394CODE
LOWmoss_tts_delay/configuration_moss_tts.py62CODE
LOWmoss_soundeffect_v2/pipeline_moss_soundeffect.py156CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py685CODE
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py284CODE
LOWmoss_soundeffect_v2/diffsynth/models/wan_audio_dit.py106CODE
LOW…ect_v2/diffsynth/models/wan_video_camera_controller.py44CODE
LOWmoss_soundeffect_v2/diffsynth/models/dac_vae.py805CODE
LOWmoss_soundeffect_v2/diffsynth/models/wan_video_dit.py294CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py843CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py17CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py153CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/utils.py325CODE
LOWmoss_soundeffect_v2/diffsynth/schedulers/flow_match.py7CODE
LOWclis/moss_tts_local_v1.5_app.py380CODE
LOWclis/moss_tts_local_v1.5_app.py521CODE
LOWmoss_tts_local/processing_moss_tts.py381CODE
LOWmoss_tts_local/processing_moss_tts.py495CODE
LOWmoss_tts_local/modeling_moss_tts.py187CODE
LOWmoss_tts_local/modeling_moss_tts.py542CODE
LOWmoss_tts_local/modeling_moss_tts.py642CODE
LOWmoss_tts_local/modeling_moss_tts.py708CODE
LOWmoss_tts_local/modeling_moss_tts.py778CODE
LOWmoss_tts_local/configuration_moss_tts.py62CODE
LOWmoss_tts_local_v1.5/processing_moss_tts.py280CODE
LOWmoss_tts_local_v1.5/qwen3_decoder.py467CODE
LOWmoss_tts_local_v1.5/gpt2_decoder.py595CODE
LOWmoss_tts_local_v1.5/modeling_moss_tts.py273CODE
LOWmoss_tts_local_v1.5/modeling_moss_tts.py463CODE
LOWmoss_tts_local_v1.5/streaming.py175CODE
LOWmoss_tts_local_v1.5/configuration_moss_tts.py32CODE
Over-Commented Block33 hits · 33 pts
SeverityFileLineSnippetContext
LOW…realtime/mossttsrealtime/processing_mossttsrealtime.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.COMMENT
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py1# Copyright 2025 The HuggingFace Team. All rights reserved.COMMENT
LOW…s_realtime/mossttsrealtime/modeling_mossttsrealtime.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.COMMENT
LOWmoss_tts_realtime/mossttsrealtime/__init__.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.COMMENT
LOW…ltime/mossttsrealtime/configuration_mossttsrealtime.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.COMMENT
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py1# Copyright 2026 OpenMOSS and the HuggingFace Inc. team. All rights reserved.COMMENT
LOWmoss_tts_realtime/finetuning/prepare_data.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_realtime/finetuning/dataset.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_realtime/finetuning/common.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_realtime/finetuning/sft.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_delay/processing_moss_tts.py1# coding=utf-8COMMENT
LOWmoss_tts_delay/modeling_moss_tts.py1# coding=utf-8COMMENT
LOWmoss_tts_delay/configuration_moss_tts.py1# coding=utf-8COMMENT
LOWmoss_tts_delay/inference_utils.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_delay/finetuning/prepare_data.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_delay/finetuning/dataset.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_delay/finetuning/common.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_delay/finetuning/sft.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_delay/llama_cpp/build_bridge.sh1#!/usr/bin/env bashCOMMENT
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py141 # WanVideoUnit_ImageEmbedderVAE(),COMMENT
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py281COMMENT
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py301 # camera_control_speed: Optional[float] = 1/54,COMMENT
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py321 switch_DiT_boundary: Optional[float] = 0.875,COMMENT
LOWmoss_soundeffect_v2/diffsynth/pipelines/wan_audio.py361 # "input_video": input_video, "denoising_strength": denoising_strength,COMMENT
LOWconfigs/llama_cpp/trt.yaml1# MOSS-TTS-Delay — llama.cpp Backend (TensorRT audio, maximum performance)COMMENT
LOWconfigs/llama_cpp/trt-8gb.yaml1# MOSS-TTS-Delay — 8 GB GPU config (low-memory mode)COMMENT
LOWconfigs/llama_cpp/default.yaml1# MOSS-TTS-Delay — llama.cpp Backend (ONNX audio, default)COMMENT
LOWmoss_tts_local/processing_moss_tts.py1# coding=utf-8COMMENT
LOWmoss_tts_local/configuration_moss_tts.py1# coding=utf-8COMMENT
LOWmoss_tts_local/finetuning/prepare_data.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_local/finetuning/dataset.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_local/finetuning/common.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
LOWmoss_tts_local/finetuning/sft.py1# Copyright 2026 OpenMOSS team. All rights reserved.COMMENT
Modern Structural Boilerplate17 hits · 18 pts
SeverityFileLineSnippetContext
LOW…realtime/mossttsrealtime/processing_mossttsrealtime.py179__all__ = ["MossTTSRealtimeProcessor"]CODE
LOW…_realtime/mossttsrealtime/streaming_mossttsrealtime.py1045__all__ = [CODE
LOW…s_realtime/mossttsrealtime/modeling_mossttsrealtime.py190__all__ = ["MossTTSRealtime", "MossTTSRealtimeConfig", "MossTTSRealtimeOutputWithPast", "MossTTSRealtimePretrainedModel"CODE
LOW…ltime/mossttsrealtime/configuration_mossttsrealtime.py115__all__ = ["MossTTSRealtimeConfig", "MossTTSRealtimeLocalTransformerConfig"]CODE
LOW…time/mossttsrealtime/modeling_mossttsrealtime_local.py461__all__ = [CODE
LOWmoss_tts_realtime/finetuning/prepare_data.py226logger = logging.getLogger(__name__)CODE
LOWmoss_tts_delay/processing_moss_tts_delay_with_codec.py251__all__ = ["MossTTSDelayWithCodecProcessor"]CODE
LOWmoss_tts_delay/llama_cpp/__init__.py27__all__ = ["LlamaCppPipeline", "PipelineConfig"]CODE
LOWmoss_soundeffect_v2/__init__.py6__all__ = [CODE
LOWmoss_soundeffect_v2/diffsynth/trainers/__init__.py7__all__ = [CODE
LOWclis/moss_tts_local_v1.5_app.py227 def _set_status(self, *, state: str, error: str | None = None) -> None:CODE
LOWmoss_tts_local_v1.5/__init__.py5__all__ = [CODE
LOWmoss_tts_local_v1.5/modeling_moss_tts.py47 def _set_gradient_checkpointing(self, module: nn.Module, value: bool = False) -> None:CODE
LOW⚡moss_tts_local_v1.5/modeling_moss_tts.py123 def set_input_embeddings(self, value: nn.Embedding) -> None:CODE
LOW⚡moss_tts_local_v1.5/modeling_moss_tts.py131 def set_output_embeddings(self, new_embeddings: nn.Linear) -> None:CODE
LOWmoss_tts_local_v1.5/finetuning/sft.py241def set_rank_cuda_device(accelerator: Accelerator) -> None:CODE
LOW⚡moss_tts_local_v1.5/finetuning/sft.py527def set_gradient_checkpointing_flag(module: torch.nn.Module, value: bool) -> None:CODE
Cross-File Repetition3 hits · 15 pts
SeverityFileLineSnippetContext
HIGHmoss_tts_delay/processing_moss_tts.py0<user_inst> - reference(s): {reference} - instruction: {instruction} - tokens: {tokens} - quality: {quality} - sound eveSTRING
HIGHmoss_tts_local/processing_moss_tts.py0<user_inst> - reference(s): {reference} - instruction: {instruction} - tokens: {tokens} - quality: {quality} - sound eveSTRING
HIGHmoss_tts_local_v1.5/processing_moss_tts.py0<user_inst> - reference(s): {reference} - instruction: {instruction} - tokens: {tokens} - quality: {quality} - sound eveSTRING
Structural Annotation Overuse6 hits · 9 pts
SeverityFileLineSnippetContext
LOWmoss_tts_delay/llama_cpp/README.md42### Step 1: Download pre-quantized TTS backbone & weightsCOMMENT
LOWmoss_tts_delay/llama_cpp/README.md57### Step 2: Download ONNX audio tokenizerCOMMENT
LOWmoss_tts_delay/llama_cpp/README.md66### Step 3: Build the C bridgeCOMMENT
LOWmoss_tts_delay/llama_cpp/conversion/README.md54## Step 1: Extract WeightsCOMMENT
LOWmoss_tts_delay/llama_cpp/conversion/README.md99## Step 2: Convert Backbone to GGUFCOMMENT
LOWmoss_tts_delay/llama_cpp/conversion/README.md112## Step 3: QuantizeCOMMENT
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippetContext
LOWmoss_tts_delay/llama_cpp/build_bridge.sh4# Usage:COMMENT