{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fastpitch-parallel-text-to-speech-with-pitch","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","arxiv_id":"2006.06873","date":"2020-06-11","proceeding":null,"authors":["Adrian Łańcucki"],"abstract":"We present FastPitch, a fully-parallel text-to-speech model based on FastSpeech, conditioned on fundamental frequency contours. The model predicts pitch contours during inference. By altering these predictions, the generated speech can be more expressive, better match the semantic of the utterance, and in the end more engaging to the listener. Uniformly increasing or decreasing pitch with FastPitch generates speech that resembles the voluntary modulation of voice. Conditioning on frequency contours improves the overall quality of synthesized speech, making it comparable to state-of-the-art. It does not introduce an overhead, and FastPitch retains the favorable, fully-parallel Transformer architecture, with over 900x real-time factor for mel-spectrogram synthesis of a typical utterance.","url_abs":"https://arxiv.org/abs/2006.06873v2","url_pdf":"https://arxiv.org/pdf/2006.06873v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fastpitch-parallel-text-to-speech-with-pitch","repo_url":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/FastPitch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"fastpitch-parallel-text-to-speech-with-pitch","repo_url":"https://github.com/as-ideas/ForwardTacotron","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fastpitch-parallel-text-to-speech-with-pitch","repo_url":"https://github.com/coqui-ai/TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MPL-2.0"}},{"paper_slug":"fastpitch-parallel-text-to-speech-with-pitch","repo_url":"https://github.com/huseinzol05/malaya-speech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fastpitch-parallel-text-to-speech-with-pitch","repo_url":"https://github.com/PaddlePaddle/PaddleSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fastpitch-parallel-text-to-speech-with-pitch","repo_url":"https://github.com/keonlee9420/FastPitchFormant","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fastpitch","method_name":"FastPitch"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"fastpitch","name":"FastPitch","full_name":"FastPitch"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.06873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06873"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleSpeech","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/FastPitch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coqui-ai/TTS","reach":{"status":"ok","spdx":"MPL-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huseinzol05/malaya-speech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/FastPitchFormant","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/as-ideas/ForwardTacotron","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":3,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"named_in_paper":{"samples":5,"ran":0,"repositories":1},"listed":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"keonlee9420/FastPitchFormant","repo_kind":"listed","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/FastPitchFormant/blob/HEAD/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"f1cba67eb6d6e4ad","entry":"get_param_num","repo":"keonlee9420/FastPitchFormant","repo_kind":"listed","path":"utils/model.py","file_url":"https://github.com/keonlee9420/FastPitchFormant/blob/HEAD/utils/model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1cba67eb6d6e4ad"}},{"code_sha256_prefix":"0f8f22937463d3c5","entry":"get_sinusoid_encoding_table","repo":"keonlee9420/FastPitchFormant","repo_kind":"listed","path":"model/modules.py","file_url":"https://github.com/keonlee9420/FastPitchFormant/blob/HEAD/model/modules.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"code_sha256_prefix":"2b5c06c1ba593c3c","entry":"read_lexicon","repo":"keonlee9420/FastPitchFormant","repo_kind":"listed","path":"synthesize.py","file_url":"https://github.com/keonlee9420/FastPitchFormant/blob/HEAD/synthesize.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b5c06c1ba593c3c"}},{"code_sha256_prefix":"a0c49128f0c91bec","entry":"generate_square_subsequent_mask","repo":"as-ideas/ForwardTacotron","repo_kind":"named_in_paper","path":"models/common_layers.py","file_url":"https://github.com/as-ideas/ForwardTacotron/blob/HEAD/models/common_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0c49128f0c91bec"}},{"code_sha256_prefix":"91d5a6e1546706d1","entry":"make_mel_len_mask","repo":"as-ideas/ForwardTacotron","repo_kind":"named_in_paper","path":"models/common_layers.py","file_url":"https://github.com/as-ideas/ForwardTacotron/blob/HEAD/models/common_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91d5a6e1546706d1"}},{"code_sha256_prefix":"ad0e751533352511","entry":"make_token_len_mask","repo":"as-ideas/ForwardTacotron","repo_kind":"named_in_paper","path":"models/common_layers.py","file_url":"https://github.com/as-ideas/ForwardTacotron/blob/HEAD/models/common_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad0e751533352511"}},{"code_sha256_prefix":"244ced1ca103e6bc","entry":"normalize_values","repo":"as-ideas/ForwardTacotron","repo_kind":"named_in_paper","path":"train_tacotron.py","file_url":"https://github.com/as-ideas/ForwardTacotron/blob/HEAD/train_tacotron.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"244ced1ca103e6bc"}},{"code_sha256_prefix":"cf6c592957959da5","entry":"valid_n_workers","repo":"as-ideas/ForwardTacotron","repo_kind":"named_in_paper","path":"preprocess.py","file_url":"https://github.com/as-ideas/ForwardTacotron/blob/HEAD/preprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf6c592957959da5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}