Home / 2noise / ChatTTS
AI Slop Code RIsk Monitor

2noise/ChatTTS

A generative speech model for daily dialogue.

6.0 Moderate pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for 2noise/ChatTTS, a Python project with 39,896 GitHub stars. SynthScan examined 31,102 lines of code across 90 source files, recording 122 pattern matches distributed across 14 syntactic categories. The legacy adjusted pattern signal is 6.0 (Moderate 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.

6.0
Adjusted Signal
6.0
Raw Pattern Score
100%
Time Factor
2026-04-10
Last Push
39.9K
Stars
Python
Language
31.1K
Lines of Code
90
Files
122
Pattern Hits
2026-10-12
Scan Date
0.10
HC Hit Rate

Risk Review · v3

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

Cognitive Ownership Risk 14.7/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 70 finding(s).

Hallucinated Dependency & Supply Chain Risk 8.9/100 · LOW

Are imports declared and package/API names verified? 42 finding(s).

Agent Over-Engineering Ratio 9.5/100 · LOW

Are wrappers, guards, and repeated structures necessary? 43 finding(s).

PR Review Velocity Impact 26.4/100 · MEDIUM

Which changes need focused human review? 122 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 9MEDIUM 12LOW 101

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 122 distinct pattern matches across 14 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.

Unused Imports38 hits · 38 pts
SeverityFileLineSnippetContext
LOWtools/llm/__init__.py1CODE
LOWtools/logger/__init__.py1CODE
LOWtools/seeder/__init__.py1CODE
LOWtools/audio/__init__.py1CODE
LOWtools/audio/__init__.py2CODE
LOWtools/audio/__init__.py2CODE
LOWtools/audio/__init__.py2CODE
LOWtools/audio/__init__.py3CODE
LOWtools/audio/__init__.py4CODE
LOWtools/normalizer/__init__.py1CODE
LOWtools/normalizer/__init__.py2CODE
LOWChatTTS/__init__.py1CODE
LOWChatTTS/config/__init__.py1CODE
LOWChatTTS/utils/__init__.py1CODE
LOWChatTTS/utils/__init__.py1CODE
LOWChatTTS/utils/__init__.py2CODE
LOWChatTTS/utils/__init__.py3CODE
LOWChatTTS/utils/__init__.py3CODE
LOWChatTTS/utils/__init__.py3CODE
LOWChatTTS/utils/__init__.py3CODE
LOWChatTTS/utils/__init__.py4CODE
LOWChatTTS/utils/gpu.py6CODE
LOWChatTTS/model/__init__.py1CODE
LOWChatTTS/model/__init__.py2CODE
LOWChatTTS/model/__init__.py3CODE
LOWChatTTS/model/__init__.py4CODE
LOWChatTTS/model/__init__.py5CODE
LOWChatTTS/model/__init__.py6CODE
LOWChatTTS/model/cuda/__init__.py1CODE
LOWChatTTS/model/velocity/llm_engine.py23CODE
LOWChatTTS/model/velocity/llm_engine.py25CODE
LOWChatTTS/model/velocity/llm_engine.py31CODE
LOWChatTTS/model/velocity/__init__.py1CODE
LOWChatTTS/model/velocity/__init__.py2CODE
LOWChatTTS/model/velocity/model_loader.py9CODE
LOWexamples/web/webui.py13CODE
LOWexamples/api/openai_api.py20CODE
LOWexamples/api/postScript.py2CODE
Self-Referential Comments12 hits · 36 pts
SeverityFileLineSnippetContext
MEDIUMtools/audio/pcm.py16 # Create an in-memory byte stream bufferCOMMENT
MEDIUMChatTTS/model/velocity/llm_engine.py104 # Create the parallel GPU workers.COMMENT
MEDIUMChatTTS/model/velocity/llm_engine.py117 # Create the scheduler.COMMENT
MEDIUMChatTTS/model/velocity/llm_engine.py312 # Create the engine configs.COMMENT
MEDIUMChatTTS/model/velocity/llm_engine.py317 # Create the LLM engine.COMMENT
MEDIUMChatTTS/model/velocity/llm_engine.py354 # Create the sequences.COMMENT
MEDIUMChatTTS/model/velocity/llm_engine.py359 # Create the sequence group.COMMENT
MEDIUMChatTTS/model/velocity/llm_engine.py624 # Create the outputs.COMMENT
MEDIUMChatTTS/model/velocity/model_loader.py53 # Create a model instance.COMMENT
MEDIUMChatTTS/model/velocity/scheduler.py83 # Create the block space manager.COMMENT
MEDIUMChatTTS/model/velocity/output.py101 # Create the outputs.COMMENT
MEDIUMexamples/api/openai_api.py35# Import necessary modulesCOMMENT
Cross-Language Confusion4 hits · 20 pts
SeverityFileLineSnippetContext
HIGHexamples/cmd/run.py41 "Run: conda install -c conda-forge pynini=2.1.5 && pip install nemo_text_processing",CODE
HIGHexamples/cmd/run.py50 "Run: conda install -c conda-forge pynini=2.1.5 && pip install WeTextProcessing",CODE
HIGHexamples/web/funcs.py99 "Run: conda install -c conda-forge pynini=2.1.5 && pip install nemo_text_processing",CODE
HIGHexamples/web/funcs.py108 "Run: conda install -c conda-forge pynini=2.1.5 && pip install WeTextProcessing",CODE
Cross-File Repetition4 hits · 20 pts
SeverityFileLineSnippetContext
HIGHREADME.md0chat t t s is a text to speech model designed for dialogue applications. [uv_break]it supports mixed language input [uv_STRING
HIGHdocs/kr/README.md0chat t t s is a text to speech model designed for dialogue applications. [uv_break]it supports mixed language input [uv_STRING
HIGHdocs/cn/README.md0chat t t s is a text to speech model designed for dialogue applications. [uv_break]it supports mixed language input [uv_STRING
HIGHdocs/es/README.md0chat t t s is a text to speech model designed for dialogue applications. [uv_break]it supports mixed language input [uv_STRING
Hyper-Verbose Identifiers20 hits · 19 pts
SeverityFileLineSnippetContext
LOWChatTTS/norm.py235 def _count_invalid_characters(self, s: str):CODE
LOWChatTTS/utils/dl.py114def download_and_extract_tar_gz(CODE
LOWChatTTS/model/gpt.py164 def _prepare_generation_inputs(CODE
LOWChatTTS/model/gpt.py291 def _prepare_generation_outputs(CODE
LOWChatTTS/model/velocity/worker.py92 def profile_num_available_blocks(CODE
LOWChatTTS/model/velocity/worker.py207def _init_distributed_environment(CODE
LOWChatTTS/model/velocity/worker.py241def _check_if_gpu_supports_dtype(torch_dtype: torch.dtype):CODE
LOWChatTTS/model/velocity/configs.py203 def verify_with_parallel_config(CODE
LOWChatTTS/model/velocity/configs.py322 def verify_with_parallel_config(CODE
LOWChatTTS/model/velocity/llm_engine.py377 def get_num_unfinished_requests(self) -> int:CODE
LOWChatTTS/model/velocity/llm_engine.py385 def _check_beam_search_early_stopping(CODE
LOWChatTTS/model/velocity/llm_engine.py429 def _process_sequence_group_outputs(CODE
LOWChatTTS/model/velocity/scheduler.py127 def get_num_unfinished_seq_groups(self) -> int:CODE
LOWexamples/onnx/exporter.py137 def convert_embedding_code_cache():CODE
LOWexamples/onnx/modeling_llama.py615 def _set_gradient_checkpointing(self, module, value=False):STRING
LOWexamples/onnx/modeling_llama.py720 def _prepare_decoder_attention_mask(STRING
LOWexamples/onnx/modeling_llama.py1041 def prepare_inputs_for_generation(CODE
LOWexamples/web/funcs.py237def set_buttons_before_generate(generate_button, interrupt_button):CODE
LOWexamples/web/funcs.py249def set_buttons_after_generate(generate_button, interrupt_button, audio_output):CODE
LOWexamples/api/main.py52async def validation_exception_handler(request, exc: RequestValidationError):CODE
Deep Nesting16 hits · 16 pts
SeverityFileLineSnippetContext
LOWChatTTS/core.py66CODE
LOWChatTTS/core.py210CODE
LOWChatTTS/core.py390CODE
LOWChatTTS/utils/dl.py19CODE
LOWChatTTS/utils/io.py41CODE
LOWChatTTS/utils/gpu.py13CODE
LOWChatTTS/model/gpt.py164CODE
LOWChatTTS/model/gpt.py324CODE
LOWChatTTS/model/velocity/sequence.py35CODE
LOWChatTTS/model/velocity/llm_engine.py429CODE
LOWChatTTS/model/velocity/llm.py193CODE
LOWChatTTS/model/velocity/scheduler.py103CODE
LOWChatTTS/model/velocity/scheduler.py130CODE
LOWexamples/cmd/stream.py74CODE
LOWexamples/onnx/modeling_llama.py1121CODE
LOWexamples/web/webui.py17CODE
AI Structural Patterns13 hits · 13 pts
SeverityFileLineSnippetContext
LOWChatTTS/core.py137CODE
LOWChatTTS/core.py210CODE
LOWChatTTS/core.py278CODE
LOWChatTTS/core.py390CODE
LOWChatTTS/model/gpt.py324CODE
LOWChatTTS/model/velocity/worker.py204CODE
LOWChatTTS/model/velocity/configs.py64CODE
LOWChatTTS/model/velocity/sampling_params.py94CODE
LOWChatTTS/model/velocity/llm.py68CODE
LOWChatTTS/model/velocity/sampler.py15CODE
LOWexamples/onnx/modeling_llama.py748CODE
LOWexamples/onnx/modeling_llama.py936CODE
LOWexamples/onnx/modeling_llama.py1121CODE
Redundant / Tautological Comments5 hits · 10 pts
SeverityFileLineSnippetContext
LOWChatTTS/model/velocity/worker.py242 # Check if the GPU supports the dtype.COMMENT
LOWChatTTS/model/velocity/llm_engine.py558 # Check if we can stop the beam search.COMMENT
LOW⚡ChatTTS/model/velocity/llm_engine.py782 # Check if the sequence has reached max_model_len.COMMENT
LOW⚡ChatTTS/model/velocity/llm_engine.py787 # Check if the sequence has reached max_tokens.COMMENT
LOW⚡ChatTTS/model/velocity/llm_engine.py792 # Check if the sequence has generated the EOS token.COMMENT
Empty Error Handlers1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHChatTTS/utils/gpu.py7except ImportError:CODE
Excessive Try-Catch Wrapping4 hits · 4 pts
SeverityFileLineSnippetContext
LOWChatTTS/norm.py212 except Exception as e:CODE
LOWChatTTS/model/gpt.py101 except Exception as e:CODE
LOWexamples/web/funcs.py128 except Exception as e:CODE
LOWexamples/api/openai_api.py217 except Exception as e:CODE
Over-Commented Block2 hits · 2 pts
SeverityFileLineSnippetContext
LOWChatTTS/model/velocity/llama.py1# coding=utf-8COMMENT
LOWexamples/onnx/modeling_llama.py1# coding=utf-8COMMENT
AI Slop Vocabulary1 hit · 2 pts
SeverityFileLineSnippetContext
LOWChatTTS/model/velocity/model_runner.py133 # yet. In this case, we just use a dummy slot mapping.COMMENT
Slop Phrases1 hit · 2 pts
SeverityFileLineSnippetContext
LOWChatTTS/model/velocity/configs.py590 # make sure to update docs/source/models/engine_args.rstCOMMENT
Modern Structural Boilerplate1 hit · 1 pts
SeverityFileLineSnippetContext
LOWChatTTS/model/velocity/model_runner.py95 def set_block_size(self, block_size: int) -> None:CODE