2noise/ChatTTS · error · ValueError
min_p must be in [0, 1], got {self.min_p}.
Error message
min_p must be in [0, 1], got {self.min_p}. What it means
SamplingParams._verify_args enforces min_p in the inclusive range [0, 1]. min_p filters tokens whose probability is below min_p times the probability of the most likely token, so it is a ratio and must lie in [0, 1].
Source
Thrown at ChatTTS/model/velocity/sampling_params.py:212
"frequency_penalty must be in [-2, 2], got "
f"{self.frequency_penalty}."
)
if not 0.0 < self.repetition_penalty <= 2.0:
raise ValueError(
"repetition_penalty must be in (0, 2], got "
f"{self.repetition_penalty}."
)
# if self.temperature < 0.0:
# raise ValueError(
# f"temperature must be non-negative, got {self.temperature}.")
if not 0.0 < self.top_p <= 1.0:
raise ValueError(f"top_p must be in (0, 1], got {self.top_p}.")
if self.top_k < -1 or self.top_k == 0:
raise ValueError(
f"top_k must be -1 (disable), or at least 1, " f"got {self.top_k}."
)
if not 0.0 <= self.min_p <= 1.0:
raise ValueError("min_p must be in [0, 1], got " f"{self.min_p}.")
if self.max_tokens < 1:
raise ValueError(f"max_tokens must be at least 1, got {self.max_tokens}.")
if self.logprobs is not None and self.logprobs < 0:
raise ValueError(f"logprobs must be non-negative, got {self.logprobs}.")
if self.prompt_logprobs is not None and self.prompt_logprobs < 0:
raise ValueError(
f"prompt_logprobs must be non-negative, got " f"{self.prompt_logprobs}."
)
def _verify_beam_search(self) -> None:
if self.best_of == 1:
raise ValueError(
"best_of must be greater than 1 when using beam "
f"search. Got {self.best_of}."
)
if self.temperature > _SAMPLING_EPS:
raise ValueError("temperature must be 0 when using beam search.")
if self.top_p < 1.0 - _SAMPLING_EPS:View on GitHub (pinned to 77b89ee281)
Solutions
- Keep min_p in [0, 1]; 0 disables min_p filtering
- Clamp or validate the value before constructing SamplingParams
Example fix
# before params = SamplingParams(min_p=1.2) # after params = SamplingParams(min_p=0.05)
Defensive patterns
Strategy: validation
Validate before calling
def clamp_min_p(v: float) -> float:
return min(max(float(v), 0.0), 1.0) Type guard
def is_valid_min_p(v) -> bool:
return isinstance(v, (int, float)) and 0.0 <= v <= 1.0 Prevention
- Clamp min_p to [0, 1] at the request boundary
- Remember 0 disables min-p filtering
When it happens
Trigger: Constructing SamplingParams with min_p < 0 or min_p > 1.0 (e.g. 1.2 or -0.1 from user input).
Common situations: Confusing min_p with an absolute probability threshold; unvalidated request payloads; porting a min_p value tuned against another implementation.
Related errors
- n must be at least 1, got {self.n}.
- best_of must be greater than or equal to n, got n={self.n} a
- presence_penalty must be in [-2, 2], got {self.presence_pena
- frequency_penalty must be in [-2, 2], got {self.frequency_pe
- repetition_penalty must be in (0, 2], got {self.repetition_p
AI-assisted analysis of 2noise/ChatTTS@77b89ee281 (2026-08-26).
Data as JSON: /api/errors/3f61585150c46a1f.
Report an issue: GitHub.