E2TTSOptions
Options & Configuration · AiDotNet.TextToSpeech.FlowDiffusion
Options for E2 TTS (Eskimez et al. 2024): a flat U-Net Transformer trained by text-guided speech-infilling flow matching.
Inheritance: ModelOptions → TtsModelOptions → E2TTSOptions
For Beginners
These options configure the F5TTS model. Default values follow the original paper settings.
How It Works
Defaults are E2 TTS as reproduced in F5-TTS (Chen et al. 2024 §4; SWivid/F5-TTS configs/E2TTS_Base.yaml):
24 layers with U-Net skips, 16 heads of 64, width 1024, feed-forward 4096 (×4), dropout 0.1, rotary embedding on the
first head; characters embedded at the mel width; a vocabulary of 2545 characters plus the filler;
24 kHz, 1024-point STFT, hop 256, 100 mel bins; infilling spans of 70–100 %, audio-condition drop 0.3, joint drop 0.2;
AdamW at 7.5e-5 warmed up linearly over 20K updates then decayed linearly, gradient clip 1; inference with 32 NFE,
sway coefficient −1 and CFG strength 2.
Constructors
| Constructor | Summary |
|---|---|
E2TTSOptions() |
Creates E2 TTS Base. |
E2TTSOptions(E2TTSOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
double AudioDropProbability { get; set; } |
Gets or sets the probability of dropping the audio condition (0.3). |
double CfgStrength { get; set; } |
Gets or sets the classifier-free guidance strength α (2). |
double ConditionDropProbability { get; set; } |
Gets or sets the probability of dropping audio and text together (0.2). |
double FramesPerCharacter { get; set; } |
Gets or sets the frames per character when synthesizing without a prompt, whose speaking rate the paper otherwise uses (6, about 15 characters per second at 93.75 frames per second). |
double MaskFractionMax { get; set; } |
Gets or sets the largest masked fraction of a training utterance (1.0). |
double MaskFractionMin { get; set; } |
Gets or sets the smallest masked fraction of a training utterance (0.7). |
double MaxGradientNorm { get; set; } |
Gets or sets the gradient-norm clip (1). |
double Speed { get; set; } |
Gets or sets the speaking-rate multiplier at synthesis (1). |
double SwayCoefficient { get; set; } |
Gets or sets the sway sampling coefficient s (−1). |
int FeedForwardMultiplier { get; set; } |
Gets or sets the feed-forward width multiplier (4: 1024/4096). |
int HeadDim { get; set; } |
Gets or sets the attention head width (64). |
int NumDecoderLayers { get; set; } |
The later half of the paired U-Net Transformer; changing either half preserves the mirrored skips. |
int NumEncoderLayers { get; set; } |
The earlier half of the paired U-Net Transformer (12 blocks in E2 TTS Base). |
int NumFunctionEvaluations { get; set; } |
Gets or sets the number of Euler steps at synthesis (32 NFE). |
int NumLayers { get; set; } |
Gets or sets the Transformer layers, an even number paired by the skip connections (24). |
int SamplingSeed { get; set; } |
Gets or sets the seed of the training draws and the sampling noise, for repeatable runs. |
int TotalSteps { get; set; } |
Gets or sets the total updates over which the rate decays linearly (1.2M). |
int WarmupSteps { get; set; } |
Gets or sets the learning-rate warmup updates (20 000). |
int? RotaryHeads { get; set; } |
Gets or sets how many leading heads carry the rotary embedding (1, the reference configuration; null for all). |