Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

chore(release): prepare FunASR 1.4.24

zhifu gao4953c6760168
diff --git a/README.md b/README.md
index f36b7a086..8c4fc4501 100644
--- a/README.md
+++ b/README.md
@@ -364,7 +364,8 @@ recordings with the same evaluation scope.
## What's new
- **MOSS-Transcribe-Diarize** brings long-form ASR, timestamps, and anonymous speaker labels to FunASR services, Docker, Kubernetes, vLLM/SGLang workflows, and FunClip. [Deploy MOSS ->](./docs/moss_transcribe_diarize.md)
-- **FunASR 1.4.23** fixes the online frontend cursor for `lfr_m=lfr_n=1` and redundant empty final offline VAD chunks. With a supplied `token_list`, SentencePiece `ids2tokens` returns model pieces; use `tokens2text` for text. Without `token_list`, legacy text decoding is unchanged. [Fix #3849](https://github.com/modelscope/FunASR/pull/3849), [fix #3783](https://github.com/modelscope/FunASR/pull/3783). Install with `python -m pip install -U "funasr==1.4.23"`. [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)
+- **FunASR 1.4.24** ignores empty non-linguistic symbols to prevent tokenizer loops, fixes padded variance normalization, and prevents CIF crashes in mixed batches containing zero-fire samples. [Fix #3852](https://github.com/modelscope/FunASR/pull/3852), [fix #3853](https://github.com/modelscope/FunASR/pull/3853), [fix #3854](https://github.com/modelscope/FunASR/pull/3854). A checkpoint trained with both `norm_means=True` and `norm_vars=True` needs recognition-quality reevaluation because normalized features change; `norm_vars=False` remains the default. Install with `python -m pip install -U "funasr==1.4.24"`. [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.24)
+ **FunASR 1.4.23** fixes the online frontend cursor for `lfr_m=lfr_n=1` and redundant empty final offline VAD chunks. With a supplied `token_list`, SentencePiece `ids2tokens` returns model pieces; use `tokens2text` for text. Without `token_list`, legacy text decoding is unchanged. [Fix #3849](https://github.com/modelscope/FunASR/pull/3849), [fix #3783](https://github.com/modelscope/FunASR/pull/3783). [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)
**FunASR 1.4.22** honors per-call `merge_length_s` and evaluates dynamic VAD silence thresholds per frame using the current segment duration, preserving the fixed-threshold opt-out. [Fix #3841](https://github.com/modelscope/FunASR/pull/3841), [fix #3833](https://github.com/modelscope/FunASR/pull/3833). [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.22)
**FunASR 1.4.21** preserves the streaming punctuation cache on empty or whitespace chunks; nonempty inference is unchanged. [Fix #3824](https://github.com/modelscope/FunASR/pull/3824). [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.21)
**FunASR 1.4.20** preserves the original optional speaker dependency failure in a chained `ImportError` when `spk_model` is requested, while ASR-only construction remains available. [Fix #3819](https://github.com/modelscope/FunASR/pull/3819). [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.20)
diff --git a/README_ja.md b/README_ja.md
index 25ee7e109..4c1aaf906 100644
--- a/README_ja.md
+++ b/README_ja.md
@@ -112,7 +112,8 @@ CER/WER をそろえて比較してください。オフラインのスループ
## 最新情報
- **MOSS-Transcribe-Diarize** を FunASR service、Docker、Kubernetes、vLLM/SGLang workflow、FunClip に統合し、長時間 ASR、timestamp、匿名 speaker label を一度に処理できます。[MOSS をデプロイ ->](./docs/moss_transcribe_diarize.md)
-- **FunASR 1.4.23** は `lfr_m=lfr_n=1` のオンライン特徴抽出のフレーム位置と、オフライン VAD の余分な空の最終チャンクを修正します。`token_list` 指定時の SentencePiece `ids2tokens` はモデルのピースを返し、テキストへの変換には `tokens2text` を使います。未指定時の従来のテキスト復号は維持します。[修正 #3849](https://github.com/modelscope/FunASR/pull/3849)、[修正 #3783](https://github.com/modelscope/FunASR/pull/3783)。`python -m pip install -U "funasr==1.4.23"` でインストールできます。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)
+- **FunASR 1.4.24** は空の非言語記号によるトークナイザーの無限ループ、パディングを含む分散正規化、発火回数ゼロのサンプルを含む混合バッチでの CIF クラッシュを修正します。[修正 #3852](https://github.com/modelscope/FunASR/pull/3852)、[修正 #3853](https://github.com/modelscope/FunASR/pull/3853)、[修正 #3854](https://github.com/modelscope/FunASR/pull/3854)。`norm_means=True` と `norm_vars=True` の両方で学習した checkpoint は正規化特徴が変わるため、認識品質の再評価が必要です。既定値は引き続き `norm_vars=False` です。`python -m pip install -U "funasr==1.4.24"` でインストールできます。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.24)
+ **FunASR 1.4.23** は `lfr_m=lfr_n=1` のオンライン特徴抽出のフレーム位置と、オフライン VAD の余分な空の最終チャンクを修正します。`token_list` 指定時の SentencePiece `ids2tokens` はモデルのピースを返し、テキストへの変換には `tokens2text` を使います。未指定時の従来のテキスト復号は維持します。[修正 #3849](https://github.com/modelscope/FunASR/pull/3849)、[修正 #3783](https://github.com/modelscope/FunASR/pull/3783)。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)
**FunASR 1.4.22** は呼び出しごとの `merge_length_s` を反映し、現在の発話区間の長さに基づいて動的 VAD 無音しきい値をフレーム単位で更新します。固定しきい値モードも維持します。[修正 #3841](https://github.com/modelscope/FunASR/pull/3841)、[修正 #3833](https://github.com/modelscope/FunASR/pull/3833)。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.22)
**FunASR 1.4.21** はストリーミング句読点処理の空入力で cache を保持します。非空推論は変更されません。[修正 #3824](https://github.com/modelscope/FunASR/pull/3824)。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.21)
**FunASR 1.4.20** は `spk_model` 指定時に任意の話者依存モジュールを読み込めない場合、元の例外を連鎖した `ImportError` で報告します。ASR のみの構築は引き続き利用できます。[修正 #3819](https://github.com/modelscope/FunASR/pull/3819)。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.20)
diff --git a/README_ko.md b/README_ko.md
index 259840723..94819a9b4 100644
--- a/README_ko.md
+++ b/README_ko.md
@@ -111,7 +111,8 @@ checkpoint/revision, 오디오 집합, 하드웨어, 배치, 워밍업, 측정
## 최신 소식
- **MOSS-Transcribe-Diarize**를 FunASR service, Docker, Kubernetes, vLLM/SGLang workflow, FunClip에 통합해 긴 오디오 ASR, timestamp, 익명 speaker label을 한 번에 처리합니다. [MOSS 배포 ->](./docs/moss_transcribe_diarize.md)
-- **FunASR 1.4.23**은 `lfr_m=lfr_n=1` 온라인 프런트엔드의 프레임 위치와 오프라인 VAD의 불필요한 빈 마지막 청크를 수정합니다. `token_list`를 지정하면 SentencePiece `ids2tokens`는 모델 토큰을 반환하며, 텍스트 변환에는 `tokens2text`를 사용합니다. 미지정 시 기존 텍스트 디코딩은 유지됩니다. [수정 #3849](https://github.com/modelscope/FunASR/pull/3849), [수정 #3783](https://github.com/modelscope/FunASR/pull/3783). `python -m pip install -U "funasr==1.4.23"`로 설치할 수 있습니다. [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)
+- **FunASR 1.4.24**는 빈 비언어 기호로 인한 토크나이저 무한 루프, 패딩이 있는 입력의 분산 정규화 오류, 발화 횟수가 0인 샘플이 섞인 배치의 CIF 충돌을 수정합니다. [수정 #3852](https://github.com/modelscope/FunASR/pull/3852), [수정 #3853](https://github.com/modelscope/FunASR/pull/3853), [수정 #3854](https://github.com/modelscope/FunASR/pull/3854). `norm_means=True`와 `norm_vars=True`를 모두 사용해 학습한 checkpoint는 정규화 특징이 달라지므로 인식 품질을 다시 평가해야 합니다. 기본값은 계속 `norm_vars=False`입니다. `python -m pip install -U "funasr==1.4.24"`로 설치할 수 있습니다. [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.24)
+ **FunASR 1.4.23**은 `lfr_m=lfr_n=1` 온라인 프런트엔드의 프레임 위치와 오프라인 VAD의 불필요한 빈 마지막 청크를 수정합니다. `token_list`를 지정하면 SentencePiece `ids2tokens`는 모델 토큰을 반환하며, 텍스트 변환에는 `tokens2text`를 사용합니다. 미지정 시 기존 텍스트 디코딩은 유지됩니다. [수정 #3849](https://github.com/modelscope/FunASR/pull/3849), [수정 #3783](https://github.com/modelscope/FunASR/pull/3783). [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)
**FunASR 1.4.22**는 호출별 `merge_length_s`를 반영하고 현재 발화 구간 길이에 따라 동적 VAD 무음 임계값을 프레임마다 갱신합니다. 고정 임계값 모드도 유지합니다. [수정 #3841](https://github.com/modelscope/FunASR/pull/3841), [수정 #3833](https://github.com/modelscope/FunASR/pull/3833). [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.22)
**FunASR 1.4.21**은 스트리밍 문장부호 처리의 빈 입력에서 cache를 유지합니다. 비어 있지 않은 추론은 변경되지 않습니다. [수정 #3824](https://github.com/modelscope/FunASR/pull/3824). [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.21)
**FunASR 1.4.20**은 `spk_model` 사용 시 선택적 화자 의존성 가져오기가 실패하면 원래 예외를 연결한 `ImportError`를 제공합니다. ASR 전용 구성은 계속 사용할 수 있습니다. [수정 #3819](https://github.com/modelscope/FunASR/pull/3819). [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.20)
diff --git a/README_zh.md b/README_zh.md
index 1c3199b47..9562ad33d 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -157,7 +157,8 @@ checkpoint/revision、音频集、硬件、批量大小、预热、计时范围
## 最新动态
- **MOSS-Transcribe-Diarize** 已接入 FunASR 服务、Docker、Kubernetes、vLLM/SGLang 工作流和 FunClip,一次完成长音频转写、时间戳与匿名说话人标注。[部署 MOSS ->](./docs/moss_transcribe_diarize_zh.md)
-- **FunASR 1.4.23** 修复 `lfr_m=lfr_n=1` 在线前端的帧游标和离线 VAD 多余的空尾块。提供 `token_list` 时,SentencePiece 的 `ids2tokens` 返回模型词元,请用 `tokens2text` 转为文本;未提供 `token_list` 时保持旧有文本解码行为。[修复 #3849](https://github.com/modelscope/FunASR/pull/3849)、[修复 #3783](https://github.com/modelscope/FunASR/pull/3783)。安装:`python -m pip install -U "funasr==1.4.23"`。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)
+- **FunASR 1.4.24** 忽略空的非语言符号以避免分词死循环,修复带填充输入的方差归一化,并避免包含零触发样本的混合批次导致 CIF 崩溃。[修复 #3852](https://github.com/modelscope/FunASR/pull/3852)、[修复 #3853](https://github.com/modelscope/FunASR/pull/3853)、[修复 #3854](https://github.com/modelscope/FunASR/pull/3854)。同时启用 `norm_means=True` 和 `norm_vars=True` 训练的 checkpoint 会收到不同的归一化特征,需要重新评估识别质量;默认仍为 `norm_vars=False`。安装:`python -m pip install -U "funasr==1.4.24"`。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.24)
+ **FunASR 1.4.23** 修复 `lfr_m=lfr_n=1` 在线前端的帧游标和离线 VAD 多余的空尾块。提供 `token_list` 时,SentencePiece 的 `ids2tokens` 返回模型词元,请用 `tokens2text` 转为文本;未提供 `token_list` 时保持旧有文本解码行为。[修复 #3849](https://github.com/modelscope/FunASR/pull/3849)、[修复 #3783](https://github.com/modelscope/FunASR/pull/3783)。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)
**FunASR 1.4.22** 支持逐调用覆盖 `merge_length_s`,并根据当前语音段时长逐帧更新动态 VAD 静音阈值,同时保留固定阈值模式。[修复 #3841](https://github.com/modelscope/FunASR/pull/3841)、[修复 #3833](https://github.com/modelscope/FunASR/pull/3833)。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.22)
**FunASR 1.4.21** 在流式标点收到空白或空输入时保留 cache;非空推理保持不变。[修复 #3824](https://github.com/modelscope/FunASR/pull/3824)。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.21)
**FunASR 1.4.20** 在指定 `spk_model` 而可选说话人依赖导入失败时,通过带原始异常链的 `ImportError` 提供诊断,同时保留仅 ASR 的构造路径。[修复 #3819](https://github.com/modelscope/FunASR/pull/3819)。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.20)
diff --git a/docs/repository_roles.md b/docs/repository_roles.md
index 96aa91ed4..5fd68b165 100644
--- a/docs/repository_roles.md
+++ b/docs/repository_roles.md
@@ -5,7 +5,7 @@ This document explains the responsibility boundaries, user entry points, and iss
> **Directional roadmap, not a release promise.**
> This document records shipped capabilities and active work, but does not commit to
> future version numbers or dates. The current Python release is
-> [`funasr==1.4.23`](https://github.com/modelscope/FunASR/releases/tag/v1.4.23).
+> [`funasr==1.4.24`](https://github.com/modelscope/FunASR/releases/tag/v1.4.24).
> Any future breaking release still requires a maintainer-approved milestone and
> migration plan.
diff --git a/docs/repository_roles_zh.md b/docs/repository_roles_zh.md
index c0214965e..597bc1c69 100644
--- a/docs/repository_roles_zh.md
+++ b/docs/repository_roles_zh.md
@@ -4,7 +4,7 @@
> **方向性路线图,不是版本承诺。**
> 本文档记录已交付能力与正在推进的工作,但不承诺未来版本号或日期。当前 Python
-> 版本是 [`funasr==1.4.23`](https://github.com/modelscope/FunASR/releases/tag/v1.4.23)。
+> 版本是 [`funasr==1.4.24`](https://github.com/modelscope/FunASR/releases/tag/v1.4.24)。
> 任何未来的 breaking release 仍需 maintainer 确认 milestone 与迁移方案。
---
diff --git a/funasr/version.txt b/funasr/version.txt
index 580ef4b6c..de64192cf 100644
--- a/funasr/version.txt
+++ b/funasr/version.txt
@@ -1 +1 @@
-1.4.23
+1.4.24
diff --git a/tests/test_release_version_contract.py b/tests/test_release_version_contract.py
index 621d3ed83..a0c64371c 100644
--- a/tests/test_release_version_contract.py
+++ b/tests/test_release_version_contract.py
@@ -4,18 +4,21 @@ import pytest
ROOT = Path(__file__).resolve().parents[1]
-RELEASE_VERSION = "1.4.23"
+RELEASE_VERSION = "1.4.24"
README_FILES = ("README.md", "README_zh.md", "README_ja.md", "README_ko.md")
REPOSITORY_ROLE_FILES = ("docs/repository_roles.md", "docs/repository_roles_zh.md")
@pytest.mark.parametrize("name", README_FILES)
-def test_release_summary_covers_no_lfr_and_tokenizer_vocabulary(name):
+def test_release_summary_covers_tokenizer_normalizer_and_cif(name):
summaries = [line for line in (ROOT / name).read_text(encoding="utf-8").splitlines()
if f"**FunASR {RELEASE_VERSION}**" in line]
assert len(summaries) == 1
- assert "lfr_m=lfr_n=1" in summaries[0]
- assert "token_list" in summaries[0]
- assert "https://github.com/modelscope/FunASR/pull/3849" in summaries[0]
- assert "https://github.com/modelscope/FunASR/pull/3783" in summaries[0]
+ assert "CIF" in summaries[0]
+ assert "norm_means=True" in summaries[0]
+ assert "norm_vars=True" in summaries[0]
+ assert "norm_vars=False" in summaries[0]
+ for number in (3852, 3853, 3854):
+ assert f"https://github.com/modelscope/FunASR/pull/{number}" in summaries[0]
+ assert "checkpoint" in summaries[0]