Methods › Audio › Text-to-Speech Models › FastPitch
FastPitch
Introduced by Adrian Łańcucki in FastPitch: Parallel Text-to-speech with Pitch Prediction
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
FastPitch is a fully-parallel text-to-speech model based on FastSpeech, conditioned on fundamental frequency contours. The architecture of FastPitch is shown in the Figure. It is based on FastSpeech and composed mainly of two feed-forward Transformer (FFTr) stacks. The first one operates in the resolution of input tokens, the second one in the resolution of the output frames. Let x=(x₁, …, xₙ) be the sequence of input lexical units, and y=(y₁, …, yₜ) be the sequence of target mel-scale spectrogram frames. The first FFTr stack produces the hidden representation h=FFTr(x). The hidden representation h is used to make predictions about the duration and average pitch of every character with a 1-D CNN
d̂= DurationPredictor (h), p̂=PitchPredictor(h)
where d̂ ∈ℕⁿ and p̂ ∈ℝⁿ. Next, the pitch is projected to match the dimensionality of the hidden representation h ∈ ℝ^(n ×d) and added to h. The resulting sum g is discretely upsampled and passed to the output FFTr, which produces the output mel-spectrogram sequence
g=h+PitchEmbedding(p)
ŷ=FFTr([g₁, …, g₁_(d₁), …gₙ, …, gₙ_(dₙ)])
Ground truth p and d are used during training, and predicted p̂ and d̂ are used during inference. The model optimizes mean-squared error (MSE) between the predicted and ground-truth modalities
ℒ=‖ŷ-y‖₂²+α‖p̂-p‖₂²+γ‖d̂-d‖₂²
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2006.06873'). Repositories: 6 listed of 6 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2006.06873, not a method entry. This answer is about arXiv:2006.06873, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2006.06873 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 3 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 9 · with a code link: 4 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 9 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 9 of 9, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Efficient training strategies for natural sounding speech synthesis and speaker adaptation based on FastPitch 9 Oct 2024 · 0 repositories · arXiv:2410.06787
-
Attempt Towards Stress Transfer in Speech-to-Speech Machine Translation 7 Mar 2024 · 0 repositories · arXiv:2403.04178
-
Incremental FastPitch: Chunk-based High Quality Text to Speech 3 Jan 2024 · 0 repositories · arXiv:2401.01755
-
Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning 7 Nov 2023 · 1 repository · arXiv:2311.04313
-
Towards Building Text-To-Speech Systems for the Next Billion Users 17 Nov 2022 · 2 repositories · arXiv:2211.09536Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch 12 Apr 2022 · 0 repositories · arXiv:2204.05753
-
Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows 3 Mar 2022 · 1 repository · arXiv:2203.01786
-
Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech 14 Oct 2021 · 0 repositories · arXiv:2110.07192
-
FastPitch: Parallel Text-to-speech with Pitch Prediction 11 Jun 2020 · 6 repositories · arXiv:2006.06873Syntology official: no sample here; runs from other or unrecorded repositories · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 3 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 28 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections