{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SRILMXVWYXJRVT46BHLJEXIJYG","short_pith_number":"pith:SRILMXVW","schema_version":"1.0","canonical_sha256":"9450b65eb6c5d31acf9e09d6925d09c18bd2d674c8a83fc0b1516f94c2f27d7d","source":{"kind":"arxiv","id":"2501.14350","version":1},"attestation_state":"computed","paper":{"title":"FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Feng-Long Xie, Kai-Tuo Xu, Xu Tang, Yao Hu","submitted_at":"2025-01-24T09:21:41Z","abstract_excerpt":"We present FireRedASR, a family of large-scale automatic speech recognition (ASR) models for Mandarin, designed to meet diverse requirements in superior performance and optimal efficiency across various applications. FireRedASR comprises two variants:\n  FireRedASR-LLM: Designed to achieve state-of-the-art (SOTA) performance and to enable seamless end-to-end speech interaction. It adopts an Encoder-Adapter-LLM framework leveraging large language model (LLM) capabilities. On public Mandarin benchmarks, FireRedASR-LLM (8.3B parameters) achieves an average Character Error Rate (CER) of 3.05%, surp"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.14350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-24T09:21:41Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6eb77f544d148d6d1ecfcca941c846630cbbdab110dc10bb5a5c17a43f3c226e","abstract_canon_sha256":"76db78033e0077460ec92b3a642e5ca8cb61f2962d52d49c9b9725610b7600ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:49.373879Z","signature_b64":"xv4Ym9Uwju6u59YAzSfZBdNhNIWfD9wgsJGD4XPXCnxLiyH+Owmqg1I/SwjJrLvrnuMY8eBLEq2N6RAO7idwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9450b65eb6c5d31acf9e09d6925d09c18bd2d674c8a83fc0b1516f94c2f27d7d","last_reissued_at":"2026-07-05T10:04:49.373376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:49.373376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Feng-Long Xie, Kai-Tuo Xu, Xu Tang, Yao Hu","submitted_at":"2025-01-24T09:21:41Z","abstract_excerpt":"We present FireRedASR, a family of large-scale automatic speech recognition (ASR) models for Mandarin, designed to meet diverse requirements in superior performance and optimal efficiency across various applications. FireRedASR comprises two variants:\n  FireRedASR-LLM: Designed to achieve state-of-the-art (SOTA) performance and to enable seamless end-to-end speech interaction. It adopts an Encoder-Adapter-LLM framework leveraging large language model (LLM) capabilities. On public Mandarin benchmarks, FireRedASR-LLM (8.3B parameters) achieves an average Character Error Rate (CER) of 3.05%, surp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14350","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.14350/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.14350","created_at":"2026-07-05T10:04:49.373446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14350v1","created_at":"2026-07-05T10:04:49.373446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14350","created_at":"2026-07-05T10:04:49.373446+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRILMXVWYXJR","created_at":"2026-07-05T10:04:49.373446+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRILMXVWYXJRVT46","created_at":"2026-07-05T10:04:49.373446+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRILMXVW","created_at":"2026-07-05T10:04:49.373446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01733","citing_title":"Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07015","citing_title":"Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05852","citing_title":"UniVoice: A Unified Model for Speech and Singing Voice Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05763","citing_title":"M2S-AVSR: Modality-aware Multi-view Self-supervised Representation for Robust Audio-Visual Speech Recognition","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05121","citing_title":"Audio Interaction Model","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30366","citing_title":"Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27258","citing_title":"PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28480","citing_title":"Audio-Mind: An Auditable Agentic Framework for Audio Understanding","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29430","citing_title":"Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23598","citing_title":"When Youth Enter the Algorithmic Wild: Discovering and Understanding Potentially Harmful Teen Videos on Douyin and Kwai","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15045","citing_title":"LLMs and Speech: Integration vs. Combination","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08961","citing_title":"Dolphin-CN-Dialect: Where Chinese Dialects Matter","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04613","citing_title":"VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09121","citing_title":"Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG","json":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG.json","graph_json":"https://pith.science/api/pith-number/SRILMXVWYXJRVT46BHLJEXIJYG/graph.json","events_json":"https://pith.science/api/pith-number/SRILMXVWYXJRVT46BHLJEXIJYG/events.json","paper":"https://pith.science/paper/SRILMXVW"},"agent_actions":{"view_html":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG","download_json":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG.json","view_paper":"https://pith.science/paper/SRILMXVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14350&json=true","fetch_graph":"https://pith.science/api/pith-number/SRILMXVWYXJRVT46BHLJEXIJYG/graph.json","fetch_events":"https://pith.science/api/pith-number/SRILMXVWYXJRVT46BHLJEXIJYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG/action/storage_attestation","attest_author":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG/action/author_attestation","sign_citation":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG/action/citation_signature","submit_replication":"https://pith.science/pith/SRILMXVWYXJRVT46BHLJEXIJYG/action/replication_record"}},"created_at":"2026-07-05T10:04:49.373446+00:00","updated_at":"2026-07-05T10:04:49.373446+00:00"}