diff --git a/Issues.md b/Issues.md index 4c58224..28678ee 100644 --- a/Issues.md +++ b/Issues.md @@ -1,3 +1,17 @@ +## Reporting Other Errors + +I do not have all possible errors documented, so if you encounter one that you can't resolve, please open an Issue with adequate information, including: +* python version +* GPU +* stack trace (or full console output preferred), wrapped in \`\`\`\[trace\]\`\`\` +* summary of what you were doing + +and I'll try my best to remedy it, even if it's something small like not reading the documentation. + +***Please, please, please*** provide either a full stack trace of the error (if running the web UI) or the command prompt output (if running a script). I will not know what's wrong if you only provide the error message itself, as errors are heavily predicated on the full state it happened. Without it, I cannot help you, as I would only be able to make assumptions. + +If this is an issue related to a model being trained, ***please, please, please*** include information about your training parameters and the graphs. I cannot easily offer ***any*** insight if I do not know what I'm diagnosing. + ## Pitfalls You May Encounter I'll try and make a list of "common" (or what I feel may be common that I experience) issues with getting TorToiSe set up: @@ -34,9 +48,7 @@ Lately, it seems it just takes way too long to download Voicefixer's models. Jus ### `torch.cuda.OutOfMemoryError: CUDA out of memory.` -#### Generation - -You most likely have a GPU with low VRAM (~4GiB), and the small optimizations with keeping data on the GPU is enough to OOM. Please check the `Low VRAM` option under the `Settings` tab. +For generating: you most likely have a GPU with low VRAM (~4GiB), and the small optimizations with keeping data on the GPU is enough to OOM. Please check the `Low VRAM` option under the `Settings` tab. If you do have a beefy GPU: * if you have very large voice input files, increase the `Voice Chunk` slider, as the scripts will try and compute a voice's latents in pieces, rather than in one chunk. @@ -45,9 +57,7 @@ If you do have a beefy GPU: * if you're getting this during a `voicefixer` pass, while using CUDA for it is enabled, please try disabling CUDA for Voice Fixer under the `Settings` tab, as it has its own model it loads into VRAM. * if you're trying to create an LJSpeech dataset under `Train` > `Prepare Dataset`, please use a smaller Whisper model size under `Settings`. -#### Training - -On Pascal-and-before cards, training is pretty much an impossible feat, as consumer cards lack the VRAM necessary to train, or the dedicated silicon to leverage optimizations like BitsAndBytes. +For training: on Pascal-and-before cards, training is pretty much an impossible feat, as consumer cards lack the VRAM necessary to train, or the dedicated silicon to leverage optimizations like BitsAndBytes. If you have a Turing (or beyond) card, you may have too large of a batch size, or a mega batch factor. Please try and reduce it before trying again, and ensure TorToiSe is NOT loaded by using the `Do Not Load TTS On Startup` option and restarting the web UI. @@ -102,15 +112,3 @@ Open a command prompt and type `tskill python` to kill all Python processes. Rel ### `local_state[k] = v[grad_accum_step] / IndexError: list index out of range` Your `Gradiant Accumulation Size` is too large for your given `Batch Size`. Please reduce it to, at most, half your batch size, or use the validation button to correct this. - -## Reporting Other Errors - -I do not have all possible errors documented, so if you encounter one that you can't resolve, please open an Issue with adequate information, including: -* python version -* GPU -* stack trace (or full console output preferred), wrapped in \`\`\`\[trace\]\`\`\` -* summary of what you were doing - -and I'll try my best to remedy it, even if it's something small like not reading the documentation. - -***Please, please, please*** provide either a full stack trace of the error (if running the web UI) or the command prompt output (if running a script). I will not know what's wrong if you only provide the error message itself, as errors are heavily predicated on the full state it happened. Without it, I cannot help you, as I would only be able to make assumptions.