ErrLookup › 2noise/ChatTTS

2noise/ChatTTS

A generative speech model for daily dialogue. · Python · 53 source files

Analyzed at 77b89ee281 on 2026-08-26. 21 documented errors.

Code / Message	Type	Severity	Tags
User-specified max_model_len	validation	error	max-model-len, context-length, rope-scaling, configuration
dtype ' ' is not supported in ROCm. Supported dtypes are	validation	error	rocm, dtype, amd, gpu, configuration
The quantization method	validation	error	quantization, awq, gptq, cuda-capability, gpu
The model's max seq len	validation	critical	gpu-memory, kv-cache, max-model-len, context-length
Ray does not allocate any GPUs on the driver node. Consider…	validation	critical	ray, distributed, gpu-scheduling, placement-group
is not supported for quantization method . Supported dtypes	validation	error	quantization, dtype, vllm, gpu, model-loading
max_num_batched_tokens	validation	error
Either prompts or prompt_token_ids must be provided.	validation	error	api-misuse, input-validation, generate
max_concurrent_workers is not supported yet.	exception	error	not-implemented, vllm, internal-api
The lengths of prompts and prompt_token_ids must be the…	validation	error	api-misuse, input-validation, length-mismatch
Unsupported activation	validation	error	activation, silu, llama, model-config
min_p must be in [0, 1], got	validation	error	sampling-params, validation, min-p, llm-generation
presence_penalty must be in [-2, 2], got	validation	error	sampling-params, validation, presence-penalty, llm-generation
Quantization method specified in the model config	validation	error
top_k must be -1 (disable), or at least 1, got	validation	error	sampling-params, validation, top-k, llm-generation
best_of must be greater than or equal to n, got n=	validation	error	sampling-params, validation, llm-generation, constructor
repetition_penalty must be in	validation	error	sampling-params, validation, repetition-penalty, llm-generation
frequency_penalty must be in [-2, 2], got	validation	error	sampling-params, validation, frequency-penalty, llm-generation
top_p must be in	validation	error	sampling-params, validation, top-p, nucleus-sampling
max_tokens must be at least 1, got	validation	error	sampling-params, validation, max-tokens, llm-generation
n must be at least 1, got	validation	error	sampling-params, validation, llm-generation, constructor