From c660e192719be808c0e81d25aa1309b2397c2b4b Mon Sep 17 00:00:00 2001 From: David-Wu1119 <133224895+David-Wu1119@users.noreply.github.com> Date: Wed, 11 Nov 2026 00:03:11 -0500 Subject: [PATCH 1/4] fix(postprocess): keep a space between Latin VAD segments in rich transcription AutoModel joins the tagged SenseVoice text of each VAD segment with a single space, so a long English recording reaches rich_transcription_postprocess() as several <|lang|> blocks. The function strips every block and concatenates them with no separator, so "Hello world." and "How are you?" become "Hello world.How are you?" and the last word of one segment runs into the first word of the next. Insert a space between two blocks when both boundary characters belong to a space-separated script (ASCII or Hangul). Chinese and Japanese text and emoji boundaries are still joined without a space. The same change is applied to the funasr_onnx and funasr_torch copies so the three shipped postprocessors stay identical, and the event-segment test that pinned the glued "helloworld" output now expects "hello world". Co-Authored-By: Claude Opus 5.5 --- funasr/utils/postprocess_utils.py | 11 +++++++++- .../funasr_torch/utils/postprocess_utils.py | 11 +++++++++- .../funasr_onnx/utils/postprocess_utils.py | 11 +++++++++- .../test_rich_transcription_event_segments.py | 4 +++- tests/test_rich_transcription_postprocess.py | 21 +++++++++++++++++++ 5 files changed, 54 insertions(+), 4 deletions(-) diff --git a/funasr/utils/postprocess_utils.py b/funasr/utils/postprocess_utils.py index 6a3cd2336c..cd99e1fbbe 100644 --- a/funasr/utils/postprocess_utils.py +++ b/funasr/utils/postprocess_utils.py @@ -442,6 +442,11 @@ def format_str_v2(s): return s.strip() +def _is_spaced_char(ch): + """Latin and Hangul text separates words with spaces; CJK text does not.""" + return (ch.isascii() and not ch.isspace()) or "\uac00" <= ch <= "\ud7a3" + + def rich_transcription_postprocess(s): """Rich transcription postprocess. @@ -481,6 +486,10 @@ def get_event(s): cur_ent_event = get_event(s_list[i]) if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s): new_s = new_s[:-1] - new_s += s_list[i].strip().lstrip() + segment = s_list[i].strip() + # Each VAD segment is its own <|lang|> block; keep the word boundary between them. + if segment and _is_spaced_char(new_s[-1]) and _is_spaced_char(segment[0]): + new_s += " " + new_s += segment new_s = new_s.replace("The.", " ") return new_s.strip() diff --git a/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py b/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py index 3f8d9999e6..d9e1b06436 100644 --- a/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py +++ b/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py @@ -346,6 +346,11 @@ def format_str_v2(s): return s.strip() +def _is_spaced_char(ch): + """Latin and Hangul text separates words with spaces; CJK text does not.""" + return (ch.isascii() and not ch.isspace()) or "\uac00" <= ch <= "\ud7a3" + + def rich_transcription_postprocess(s): def get_emo(s): return s[-1] if s[-1] in emo_set else None @@ -370,6 +375,10 @@ def get_event(s): cur_ent_event = get_event(s_list[i]) if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s): new_s = new_s[:-1] - new_s += s_list[i].strip().lstrip() + segment = s_list[i].strip() + # Each VAD segment is its own <|lang|> block; keep the word boundary between them. + if segment and _is_spaced_char(new_s[-1]) and _is_spaced_char(segment[0]): + new_s += " " + new_s += segment new_s = new_s.replace("The.", " ") return new_s.strip() diff --git a/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py b/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py index 343ed383aa..84e220166c 100644 --- a/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py +++ b/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py @@ -400,6 +400,11 @@ def format_str_v2(s): return s.strip() +def _is_spaced_char(ch): + """Latin and Hangul text separates words with spaces; CJK text does not.""" + return (ch.isascii() and not ch.isspace()) or "\uac00" <= ch <= "\ud7a3" + + def rich_transcription_postprocess(s): def get_emo(s): return s[-1] if s[-1] in emo_set else None @@ -424,6 +429,10 @@ def get_event(s): cur_ent_event = get_event(s_list[i]) if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s): new_s = new_s[:-1] - new_s += s_list[i].strip().lstrip() + segment = s_list[i].strip() + # Each VAD segment is its own <|lang|> block; keep the word boundary between them. + if segment and _is_spaced_char(new_s[-1]) and _is_spaced_char(segment[0]): + new_s += " " + new_s += segment new_s = new_s.replace("The.", " ") return new_s.strip() diff --git a/tests/test_rich_transcription_event_segments.py b/tests/test_rich_transcription_event_segments.py index ed756abfd8..a565b5c3cd 100644 --- a/tests/test_rich_transcription_event_segments.py +++ b/tests/test_rich_transcription_event_segments.py @@ -34,7 +34,9 @@ def test_repeated_event_only_segments_keep_following_text(postprocess, event, fo result = postprocess.rich_transcription_postprocess(text) - assert result == postprocess.event_dict[event] + "hello" + following_text + assert result == postprocess.event_dict[event] + " ".join( + filter(None, ["hello", following_text]) + ) @pytest.mark.parametrize("event", ["<|Cough|>", "<|Sneeze|>", "<|Applause|>"]) diff --git a/tests/test_rich_transcription_postprocess.py b/tests/test_rich_transcription_postprocess.py index 8e07de09eb..2cfc708ad8 100644 --- a/tests/test_rich_transcription_postprocess.py +++ b/tests/test_rich_transcription_postprocess.py @@ -32,3 +32,24 @@ def test_cough_and_sneeze_events_render_distinct_emojis(path, event, emoji): text = module.rich_transcription_postprocess(f"<|en|><|NEUTRAL|>{event}<|woitn|>hello") assert text == f"{emoji}hello" + + +@pytest.mark.parametrize("path", POSTPROCESS_UTILS, ids=lambda path: path.parts[-3]) +@pytest.mark.parametrize( + "first, second, expected", + [ + ("Hello world.", "How are you?", "Hello world. How are you?"), + ("so I went to the", "store", "so I went to the store"), + ("안녕하세요.", "감사합니다.", "안녕하세요. 감사합니다."), + ("你好。", "再见。", "你好。再见。"), + ("你好。", "Hello.", "你好。Hello."), + ], +) +def test_vad_segments_keep_a_space_between_spaced_scripts(path, first, second, expected): + module = _load(path) + tags = "<|NEUTRAL|><|Speech|><|withitn|>" + + # AutoModel joins the tagged text of each VAD segment with a single space. + text = module.rich_transcription_postprocess(f"<|en|>{tags}{first} <|en|>{tags}{second}") + + assert text == expected From 242a11caf37b1ac5d85c92e85c6bb080069c5da4 Mon Sep 17 00:00:00 2001 From: zhifu gao Date: Fri, 13 Nov 2026 00:45:03 +0800 Subject: [PATCH 2/4] fix(ci): integrate VAD spacing with current text regression sources Preserve the original PR #3872 author commit. Synchronize current main content so the exact-head text workflow includes test_type_utils_compat.py. No test removal, history rewrite, or protection bypass. Signed-off-by: LauraGPT --- .../workflows/test-funasr-onnx-package.yml | 4 +- .../workflows/test-text-postprocessing.yml | 5 + README.md | 3 +- README_ja.md | 3 +- README_ko.md | 3 +- README_zh.md | 3 +- docs/repository_roles.md | 2 +- docs/repository_roles_zh.md | 2 +- funasr/bin/_server_app.py | 4 +- funasr/utils/timestamp_tools.py | 5 + funasr/utils/type_utils.py | 8 +- funasr/version.txt | 2 +- .../libtorch/funasr_torch/paraformer_bin.py | 4 +- .../funasr_torch/utils/postprocess_utils.py | 7 +- runtime/python/onnxruntime/README.md | 10 +- .../onnxruntime/funasr_onnx/paraformer_bin.py | 8 +- .../funasr_onnx/utils/postprocess_utils.py | 7 +- runtime/python/onnxruntime/setup.py | 2 +- tests/test_funasr_onnx_installed.py | 55 ++++++++++- tests/test_funasr_onnx_release.py | 6 +- tests/test_punc_model_none.py | 2 +- tests/test_release_version_contract.py | 15 ++- tests/test_runtime_eval_native.py | 94 +++++++++++++++++++ tests/test_sentence_postprocess_timestamps.py | 20 ++++ tests/test_server_app_openai_segments.py | 28 ++++++ tests/test_timestamp_tools.py | 25 +++++ tests/test_type_utils_compat.py | 65 +++++++++++++ 27 files changed, 358 insertions(+), 34 deletions(-) create mode 100644 tests/test_type_utils_compat.py diff --git a/.github/workflows/test-funasr-onnx-package.yml b/.github/workflows/test-funasr-onnx-package.yml index f94b86e098..226421da66 100644 --- a/.github/workflows/test-funasr-onnx-package.yml +++ b/.github/workflows/test-funasr-onnx-package.yml @@ -86,7 +86,7 @@ jobs: import importlib.util from importlib.metadata import requires, version - assert version("funasr-onnx") == "0.4.9" + assert version("funasr-onnx") == "0.4.10" assert importlib.util.find_spec("torch") is None requirements = requires("funasr-onnx") or [] @@ -130,7 +130,7 @@ jobs: if: matrix.python-version == '3.12' uses: actions/upload-artifact@v7 with: - name: funasr-onnx-0.4.9 + name: funasr-onnx-0.4.10 path: dist/funasr-onnx/* if-no-files-found: error diff --git a/.github/workflows/test-text-postprocessing.yml b/.github/workflows/test-text-postprocessing.yml index 55364def5d..c851661af3 100644 --- a/.github/workflows/test-text-postprocessing.yml +++ b/.github/workflows/test-text-postprocessing.yml @@ -3,6 +3,8 @@ name: Validate text postprocessing on: pull_request: paths: + - "funasr/utils/type_utils.py" + - "tests/test_type_utils_compat.py" - "funasr/utils/postprocess_hotwords.py" - "funasr/utils/postprocess_utils.py" - "runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py" @@ -14,6 +16,8 @@ on: push: branches: [main] paths: + - "funasr/utils/type_utils.py" + - "tests/test_type_utils_compat.py" - "funasr/utils/postprocess_hotwords.py" - "funasr/utils/postprocess_utils.py" - "runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py" @@ -52,6 +56,7 @@ jobs: - name: Check hotword and rich transcription behavior without model weights run: | python -m pytest -q \ + tests/test_type_utils_compat.py \ tests/test_postprocess_hotwords.py \ tests/test_rich_transcription_postprocess.py \ tests/test_sentence_postprocess_timestamps.py \ diff --git a/README.md b/README.md index 8c4fc45012..108711e432 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 1.4.24** 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 1.4.25** restores Python 3.12 boolean argument parsing without `distutils` and preserves normalized error messages; removes synthetic leading spaces from Latin sentence timestamps while preserving boundaries and raw text. [Fix #3863](https://github.com/modelscope/FunASR/pull/3863), [fix #3866](https://github.com/modelscope/FunASR/pull/3866). Install with `python -m pip install -U "funasr==1.4.25"`. [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.25) + **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) diff --git a/README_ja.md b/README_ja.md index 4c1aaf9066..64f634fe64 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 1.4.24** 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 1.4.25** は Python 3.12 の真偽値引数を `distutils` なしで解析し、正規化されたエラーメッセージを維持します。ラテン文字で始まる文のタイムスタンプ出力から余分な先頭空白を除き、時刻境界と原文を保持します。[修正 #3863](https://github.com/modelscope/FunASR/pull/3863)、[修正 #3866](https://github.com/modelscope/FunASR/pull/3866)。`python -m pip install -U "funasr==1.4.25"` 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/v1.4.25) + **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) diff --git a/README_ko.md b/README_ko.md index 94819a9b41..caa4938595 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 1.4.24**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 1.4.25**는 Python 3.12에서 `distutils` 없이 불리언 인수를 처리하고 정규화된 오류 메시지를 유지합니다. 라틴 문자로 시작하는 문장의 타임스탬프 출력에서 불필요한 앞 공백을 제거하며 시간 경계와 원문은 보존합니다. [수정 #3863](https://github.com/modelscope/FunASR/pull/3863), [수정 #3866](https://github.com/modelscope/FunASR/pull/3866). `python -m pip install -U "funasr==1.4.25"`로 설치할 수 있습니다. [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.25) + **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) diff --git a/README_zh.md b/README_zh.md index 9562ad33d3..ec13d2f340 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 1.4.24** 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 1.4.25** 修复 Python 3.12 下不依赖 `distutils` 的布尔参数解析并保留归一化错误信息;移除拉丁文字句子时间戳中的多余前导空格,保留时间边界和原始文本。[修复 #3863](https://github.com/modelscope/FunASR/pull/3863)、[修复 #3866](https://github.com/modelscope/FunASR/pull/3866)。安装:`python -m pip install -U "funasr==1.4.25"`。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.25) + **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) diff --git a/docs/repository_roles.md b/docs/repository_roles.md index 5fd68b1653..bff0e53a91 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==1.4.24`](https://github.com/modelscope/FunASR/releases/tag/v1.4.24). +> [`funasr==1.4.25`](https://github.com/modelscope/FunASR/releases/tag/v1.4.25). > 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 597bc1c691..fd979acedf 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==1.4.24`](https://github.com/modelscope/FunASR/releases/tag/v1.4.24)。 +> 版本是 [`funasr==1.4.25`](https://github.com/modelscope/FunASR/releases/tag/v1.4.25)。 > 任何未来的 breaking release 仍需 maintainer 确认 milestone 与迁移方案。 --- diff --git a/funasr/bin/_server_app.py b/funasr/bin/_server_app.py index 588f1fbb1a..8822e94a44 100644 --- a/funasr/bin/_server_app.py +++ b/funasr/bin/_server_app.py @@ -20,7 +20,7 @@ try: from fastapi import FastAPI, UploadFile, File, Form, HTTPException from fastapi.middleware.cors import CORSMiddleware - from fastapi.responses import JSONResponse + from fastapi.responses import JSONResponse, PlainTextResponse except ImportError: raise ImportError( "funasr-server requires additional packages. Install with: pip install vllm fastapi uvicorn python-multipart" @@ -529,7 +529,7 @@ async def transcribe( if response_format == "verbose_json": return JSONResponse(build_openai_verbose_json(result, requested_language=language)) elif response_format == "text": - return JSONResponse(result["text"]) + return PlainTextResponse(result["text"]) else: return JSONResponse({"text": result["text"]}) diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py index b97e405f33..8009ec7575 100644 --- a/funasr/utils/timestamp_tools.py +++ b/funasr/utils/timestamp_tools.py @@ -189,6 +189,11 @@ def timestamp_sentence( punc_id = int(punc_id) if punc_id is not None else 1 sentence_end = timestamp[1] if timestamp is not None else sentence_end + # Latin tokens are inserted with a leading space. Drop one leading + # space, as timestamp_sentence_en does, so a sentence that starts + # with an English word is not stored as " iphone...". + if sentence_text.startswith(" "): + sentence_text = sentence_text[1:] if punc_id > 1: sentence_text += punc_list[punc_id - 2] if sentence_text_seg.endswith(" "): diff --git a/funasr/utils/type_utils.py b/funasr/utils/type_utils.py index 0731e46f88..2b2323c35e 100644 --- a/funasr/utils/type_utils.py +++ b/funasr/utils/type_utils.py @@ -1,4 +1,3 @@ -from distutils.util import strtobool from typing import Optional from typing import Tuple from typing import Union @@ -15,7 +14,12 @@ def str2bool(value: str) -> bool: Args: value: TODO. """ - return bool(strtobool(value)) + normalized = value.lower() + if normalized in ("y", "yes", "t", "true", "on", "1"): + return True + if normalized in ("n", "no", "f", "false", "off", "0"): + return False + raise ValueError(f"invalid truth value {normalized!r}") def remove_parenthesis(value: str): diff --git a/funasr/version.txt b/funasr/version.txt index de64192cf1..df3487bee1 100644 --- a/funasr/version.txt +++ b/funasr/version.txt @@ -1 +1 @@ -1.4.24 +1.4.25 diff --git a/runtime/python/libtorch/funasr_torch/paraformer_bin.py b/runtime/python/libtorch/funasr_torch/paraformer_bin.py index dc9d2a5966..93159e85c9 100644 --- a/runtime/python/libtorch/funasr_torch/paraformer_bin.py +++ b/runtime/python/libtorch/funasr_torch/paraformer_bin.py @@ -120,10 +120,10 @@ def __call__(self, wav_content: Union[str, np.ndarray, List[str]], **kwargs) -> pred = sentence_postprocess(pred) asr_res.append({"preds": pred}) else: - for pred, us_peaks_ in zip(preds, us_peaks): + for pred, us_peaks_, feat_len in zip(preds, us_peaks, feats_len): raw_tokens = pred timestamp, timestamp_raw = time_stamp_lfr6_onnx( - us_peaks_, copy.copy(raw_tokens) + us_peaks_[: feat_len * 3], copy.copy(raw_tokens) ) text_proc, timestamp_proc, _ = sentence_postprocess( raw_tokens, timestamp_raw diff --git a/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py b/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py index d9e1b06436..d5b7a6ffb3 100644 --- a/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py +++ b/runtime/python/libtorch/funasr_torch/utils/postprocess_utils.py @@ -106,17 +106,18 @@ def abbr_dispose(words: List[Any], time_stamp: List[List] = None) -> List[Any]: if num in abbr_begin: if time_stamp is not None: begin = time_stamp[ts_nums[num]][0] - word_lists.append(words[num].upper()) + abbr_word = words[num].upper() num += 1 while num < words_size: if num in abbr_end: - word_lists.append(words[num].upper()) + abbr_word += words[num].upper() last_num = num break else: if words[num].encode("utf-8").isalpha(): - word_lists.append(words[num].upper()) + abbr_word += words[num].upper() num += 1 + word_lists.append(abbr_word) if time_stamp is not None: end = time_stamp[ts_nums[num]][1] ts_lists.append([begin, end]) diff --git a/runtime/python/onnxruntime/README.md b/runtime/python/onnxruntime/README.md index 8794ac4c74..e3d18c6d43 100644 --- a/runtime/python/onnxruntime/README.md +++ b/runtime/python/onnxruntime/README.md @@ -7,6 +7,12 @@ does not update the installed ONNX wrappers. Check their versions separately with `python -m pip show funasr-onnx funasr`; use the source installation below when a required wrapper fix is newer than the published PyPI package. +Version 0.4.10 restores direct librosa decoding for non-WAV audio in offline +and streaming Paraformer, SenseVoice and offline VAD (#3865), without creating a WAV sidecar +or treating every non-WAV input as MP3. Codec support still depends on the +installed audio backend. This is a runtime loading fix, not a model-weight +or ASR accuracy update. + Version 0.4.9 keeps one result per input when offline VAD receives empty or sub-frame audio, without invoking ONNX Runtime for zero-frame features (#3846). It also returns an empty punctuation chunk while it preserves the streaming cache and avoids @@ -39,9 +45,9 @@ and postprocessing fixes, not a model-weight update or an ASR accuracy claim. install from pip ```shell -pip install -U "funasr-onnx>=0.4.9" +pip install -U "funasr-onnx>=0.4.10" # For the users in China, you could install with the command: -# pip install -U "funasr-onnx>=0.4.9" -i https://mirror.sjtu.edu.cn/pypi/web/simple +# pip install -U "funasr-onnx>=0.4.10" -i https://mirror.sjtu.edu.cn/pypi/web/simple # If you want to export .onnx file, you should install modelscope and funasr pip install -U modelscope funasr # For the users in China, you could install with the command: diff --git a/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py b/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py index 517252cd85..5a2da21893 100644 --- a/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py +++ b/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py @@ -131,10 +131,10 @@ def __call__(self, wav_content: Union[str, np.ndarray, List[str]], **kwargs) -> pred = sentence_postprocess(pred) asr_res.append({"preds": pred}) else: - for pred, us_peaks_ in zip(preds, us_peaks): + for pred, us_peaks_, feat_len in zip(preds, us_peaks, feats_len): raw_tokens = pred timestamp, timestamp_raw = time_stamp_lfr6_onnx( - us_peaks_, copy.copy(raw_tokens) + us_peaks_[: feat_len * 3], copy.copy(raw_tokens) ) text_proc, timestamp_proc, _ = sentence_postprocess( raw_tokens, timestamp_raw @@ -384,10 +384,10 @@ def __call__( pred = sentence_postprocess(pred) asr_res.append({"preds": pred}) else: - for pred, us_peaks_ in zip(preds, us_peaks): + for pred, us_peaks_, feat_len in zip(preds, us_peaks, feats_len): raw_tokens = pred timestamp, timestamp_raw = time_stamp_lfr6_onnx( - us_peaks_, copy.copy(raw_tokens) + us_peaks_[: feat_len * 3], copy.copy(raw_tokens) ) text_proc, timestamp_proc, _ = sentence_postprocess( raw_tokens, timestamp_raw diff --git a/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py b/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py index 84e220166c..82c334f855 100644 --- a/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py +++ b/runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py @@ -108,17 +108,18 @@ def abbr_dispose(words: List[Any], time_stamp: List[List] = None) -> List[Any]: if num in abbr_begin: if time_stamp is not None: begin = time_stamp[ts_nums[num]][0] - word_lists.append(words[num].upper()) + abbr_word = words[num].upper() num += 1 while num < words_size: if num in abbr_end: - word_lists.append(words[num].upper()) + abbr_word += words[num].upper() last_num = num break else: if words[num].encode("utf-8").isalpha(): - word_lists.append(words[num].upper()) + abbr_word += words[num].upper() num += 1 + word_lists.append(abbr_word) if time_stamp is not None: end = time_stamp[ts_nums[num]][1] ts_lists.append([begin, end]) diff --git a/runtime/python/onnxruntime/setup.py b/runtime/python/onnxruntime/setup.py index b5236ffc16..40290072f7 100644 --- a/runtime/python/onnxruntime/setup.py +++ b/runtime/python/onnxruntime/setup.py @@ -13,7 +13,7 @@ def get_readme(): MODULE_NAME = "funasr_onnx" -VERSION_NUM = "0.4.9" +VERSION_NUM = "0.4.10" setuptools.setup( name=MODULE_NAME, diff --git a/tests/test_funasr_onnx_installed.py b/tests/test_funasr_onnx_installed.py index 4b3c254ee9..b6a74c78ef 100644 --- a/tests/test_funasr_onnx_installed.py +++ b/tests/test_funasr_onnx_installed.py @@ -19,6 +19,8 @@ raise unittest.SkipTest('Install the standalone funasr-onnx distribution first.') import funasr_onnx +import numpy as np +import soundfile as sf from funasr_onnx.paraformer_online_bin import Paraformer as ParaformerOnline @@ -36,9 +38,60 @@ class InstalledOnnxPackageTest(unittest.TestCase): + LOADERS = (funasr_onnx.Paraformer, ParaformerOnline, + funasr_onnx.SenseVoiceSmall, funasr_onnx.Fsmn_vad) + + def test_lossless_non_wav_without_sidecar(self): + samples = (np.arange(4800, dtype=np.int16) - 2400).astype(np.float32) / 32768 + with tempfile.TemporaryDirectory() as directory: + path = Path(directory) / 'sample.flac' + sf.write(path, samples, 16000, subtype='PCM_16') + before = path.read_bytes() + for cls in self.LOADERS: + with self.subTest(loader=cls.__module__): + result = cls.__new__(cls).load_data(str(path), fs=16000) + self.assertEqual(len(result), 1) + np.testing.assert_array_equal(result[0], samples) + self.assertEqual(path.read_bytes(), before) + self.assertEqual(sorted(p.name for p in path.parent.iterdir()), ['sample.flac']) + + def test_wav_and_flac_list_preserves_input_order(self): + first = np.full(800, 0.125, dtype=np.float32) + second = np.full(1200, -0.25, dtype=np.float32) + with tempfile.TemporaryDirectory() as directory: + paths = [Path(directory) / 'first.wav', Path(directory) / 'second.flac'] + for path, samples in zip(paths, [first, second]): + sf.write(path, samples, 16000, subtype='PCM_16') + for cls in self.LOADERS: + with self.subTest(loader=cls.__module__): + result = cls.__new__(cls).load_data([str(p) for p in paths], fs=16000) + self.assertEqual(len(result), 2) + np.testing.assert_array_equal(result[0], first) + np.testing.assert_array_equal(result[1], second) + self.assertEqual(sorted(p.name for p in Path(directory).iterdir()), ['first.wav', 'second.flac']) + + def test_waveform_array_is_preserved(self): + samples = np.linspace(-0.25, 0.25, 320, dtype=np.float32) + for cls in self.LOADERS: + with self.subTest(loader=cls.__module__): + result = cls.__new__(cls).load_data(samples, fs=16000) + self.assertEqual(len(result), 1) + self.assertIs(result[0], samples) + + def test_invalid_audio_remains_visible_without_sidecar(self): + with tempfile.TemporaryDirectory() as directory: + path = Path(directory) / 'invalid.flac' + path.write_bytes(b'not audio') + for cls in self.LOADERS: + with self.subTest(loader=cls.__module__): + with self.assertRaises(Exception): + cls.__new__(cls).load_data(str(path), fs=16000) + self.assertEqual(path.read_bytes(), b'not audio') + self.assertEqual(sorted(p.name for p in path.parent.iterdir()), ['invalid.flac']) + def test_installed_distribution_version_and_origin(self): distribution = importlib.metadata.distribution('funasr-onnx') - self.assertEqual(distribution.version, '0.4.9') + self.assertEqual(distribution.version, '0.4.10') self.assertEqual( Path(funasr_onnx.__file__).resolve().parent, Path(distribution.locate_file('funasr_onnx')).resolve(), diff --git a/tests/test_funasr_onnx_release.py b/tests/test_funasr_onnx_release.py index 160c24aa4c..cb57f6be51 100644 --- a/tests/test_funasr_onnx_release.py +++ b/tests/test_funasr_onnx_release.py @@ -7,7 +7,7 @@ ROOT = Path(__file__).resolve().parents[1] PACKAGE_ROOT = ROOT / "runtime" / "python" / "onnxruntime" SETUP_PATH = PACKAGE_ROOT / "setup.py" -EXPECTED_VERSION = "0.4.9" +EXPECTED_VERSION = "0.4.10" REQUIREMENT_NAME_PATTERN = re.compile(r"^\s*([A-Za-z0-9](?:[A-Za-z0-9._-]*[A-Za-z0-9])?)") @@ -44,7 +44,7 @@ def normalized_requirement_name(requirement): class FunASROnnxReleaseContractTest(unittest.TestCase): - def test_release_version_is_0_4_9(self): + def test_release_version_is_0_4_10(self): self.assertEqual(assigned_literal(read_setup_tree(), "VERSION_NUM"), EXPECTED_VERSION) def test_standalone_license_preserves_repository_notice(self): @@ -68,6 +68,8 @@ def test_readme_names_the_standalone_fix_release(self): readme = (PACKAGE_ROOT / "README.md").read_text() self.assertIn(f'pip install -U "funasr-onnx>={EXPECTED_VERSION}"', readme) self.assertIn("does not update the installed ONNX wrappers", readme) + self.assertIn("#3865", readme) + self.assertIn("without creating a WAV sidecar", readme) self.assertIn("short/final VAD", readme) self.assertIn("zero-overlap", readme) self.assertIn("one independent result per input", readme) diff --git a/tests/test_punc_model_none.py b/tests/test_punc_model_none.py index 42dfe34e60..d827bca019 100644 --- a/tests/test_punc_model_none.py +++ b/tests/test_punc_model_none.py @@ -796,7 +796,7 @@ def test_chinese_vad_boundaries_remove_rich_tags_only_for_alignment(self): def test_mixed_vad_boundaries_preserve_timestamp_units(self): self._check_vad_chunk_alignment( ["你 好 hello", "world 我 来"], - ["你好 hello,", " world 我来。"], + ["你好 hello,", "world 我来。"], "你 好 hello world 我 来", raw_text=True, ) diff --git a/tests/test_release_version_contract.py b/tests/test_release_version_contract.py index a0c64371c7..d2b076db28 100644 --- a/tests/test_release_version_contract.py +++ b/tests/test_release_version_contract.py @@ -4,13 +4,13 @@ ROOT = Path(__file__).resolve().parents[1] -RELEASE_VERSION = "1.4.24" +RELEASE_VERSION = "1.4.25" 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_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] + if "**FunASR 1.4.24**" in line] assert len(summaries) == 1 assert "CIF" in summaries[0] assert "norm_means=True" in summaries[0] @@ -20,6 +20,17 @@ def test_release_summary_covers_tokenizer_normalizer_and_cif(name): assert f"https://github.com/modelscope/FunASR/pull/{number}" in summaries[0] assert "checkpoint" in summaries[0] +@pytest.mark.parametrize("name", README_FILES) +def test_release_summary_covers_parser_and_timestamp_fixes(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 "Python 3.12" in summaries[0] + assert "distutils" in summaries[0] + for number in (3863, 3866): + assert f"https://github.com/modelscope/FunASR/pull/{number}" in summaries[0] + + diff --git a/tests/test_runtime_eval_native.py b/tests/test_runtime_eval_native.py index e0e6154800..ee8d9933b4 100644 --- a/tests/test_runtime_eval_native.py +++ b/tests/test_runtime_eval_native.py @@ -8,6 +8,7 @@ import json import os from pathlib import Path +import shutil import subprocess import sys import wave @@ -275,6 +276,99 @@ def test_hotword_wrappers_decode_every_batch( assert model(paths, hotwords) == alone +@pytest.fixture(scope="module") +def timestamp_fixture(hotword_fixture, tmp_path_factory): + np = pytest.importorskip("numpy") + source, _ = hotword_fixture + directory = tmp_path_factory.mktemp("runtime-timestamp") + # The graphs only have to load: the timestamp test replaces the acoustic model's session. + for name, target in [ + ("tokens.json", "tokens.json"), + ("model_eb.onnx", "model_eb.onnx"), + ("model.onnx", "model.onnx"), + ("model_bb.torchscript", "model.torchscript"), + ]: + shutil.copy(source / name, directory / target) + (directory / "config.yaml").write_text( + json.dumps( + { + "frontend_conf": {"n_mels": 4, "lfr_m": 7, "lfr_n": 6, "dither": 0.0}, + "model_conf": {"predictor_bias": 1}, + } + ) + ) + (directory / "am.mvn").write_text( + " 28 28\n 1 [ " + "0 " * 28 + "]\n" + " 28 28\n 1 [ " + "1 " * 28 + "]\n" + ) + paths = [] + for seconds in (1, 3): + path = directory / f"tone {seconds}s.wav" + tone = np.sin(np.arange(16000 * seconds) * 2 * np.pi * 440 / 16000) * 3000 + with wave.open(str(path), "wb") as output: + output.setnchannels(1) + output.setsampwidth(2) + output.setframerate(16000) + output.writeframes(tone.astype(" + us_alphas = np.zeros((batch, 3 * feats.shape[1]), dtype=np.float32) + us_peaks = np.zeros_like(us_alphas) + for row, feat_len in enumerate(np.asarray(feats_len).tolist()): + frames = 3 * feat_len + us_alphas[row, :frames] = 3.0 / frames + us_peaks[row, np.linspace(5, frames - 6, 3).round().astype(int)] = 1.0 + return [am_scores, np.full(batch, 3, dtype=np.int32), us_alphas, us_peaks] + + +@pytest.mark.parametrize( + "backend, wrapper", + [ + ("onnx", "Paraformer"), + ("onnx", "ContextualParaformer"), + ("onnx", "SeacoParaformer"), + ("torch", "Paraformer"), + ], +) +def test_batched_timestamps_ignore_padding(timestamp_fixture, monkeypatch, backend, wrapper): + torch = pytest.importorskip("torch") + directory, paths = timestamp_fixture + location = "libtorch" if backend == "torch" else "onnxruntime" + monkeypatch.syspath_prepend(str(ROOT / "runtime/python" / location)) + module = importlib.import_module("funasr_" + backend + ".paraformer_bin") + model = getattr(module, wrapper)(str(directory), batch_size=2, intra_op_num_threads=1) + if backend == "torch": + model.ort_infer = lambda feats, feats_len: tuple( + torch.from_numpy(output) for output in timestamp_outputs(feats, feats_len) + ) + elif wrapper == "Paraformer": + model.ort_infer = lambda inputs: timestamp_outputs(*inputs) + else: + model.ort_infer_bb = lambda inputs: timestamp_outputs(*inputs[:2]) + hotwords = () if wrapper == "Paraformer" else ("魔搭",) + alone = [model(path, *hotwords)[0] for path in paths] + # The 1 s tone ends at 1000 ms, the 3 s tone at 3000 ms. + assert [row["timestamp"] for row in alone] == [ + [[70, 470], [470, 945]], + [[70, 670], [1450, 2925]], + ] + # Batched with the 3 s tone, the 1 s tone must not take on the padded frames. + assert model(paths, *hotwords) == alone + + @pytest.mark.parametrize("extension", ["flac", "ogg", "mp3"]) def test_onnx_wrappers_read_non_wav_paths(native_fixture, tmp_path, monkeypatch, extension): np = pytest.importorskip("numpy") diff --git a/tests/test_sentence_postprocess_timestamps.py b/tests/test_sentence_postprocess_timestamps.py index 0aa6965c76..921495097e 100644 --- a/tests/test_sentence_postprocess_timestamps.py +++ b/tests/test_sentence_postprocess_timestamps.py @@ -96,6 +96,26 @@ def test_untimed_transcription_still_accepts_filtered_tokens(self): ("你好", ["你", "好"]), ) + def test_spelled_out_letters_are_one_word_with_one_timestamp(self): + self.assert_timestamps( + ["我", "用", "a", "i", "写", "代", "码"], + ["我", "用", "AI", "写", "代", "码"], + [[0, 100], [100, 200], [200, 400], [400, 500], [500, 600], [600, 700]], + ) + self.assert_timestamps( + ["i", "b", "m", "is", "here"], + ["IBM", "is", "here"], + [[0, 300], [300, 400], [400, 500]], + ) + + def test_spelled_out_letters_are_one_word_without_timestamps(self): + for path in POSTPROCESS_UTILS: + with self.subTest(path=path): + self.assertEqual( + _load_sentence_postprocess(path)(["看", "c", "c", "t", "v", "新", "闻"]), + ("看CCTV新闻", ["看", "CCTV", "新", "闻"]), + ) + if __name__ == "__main__": unittest.main() diff --git a/tests/test_server_app_openai_segments.py b/tests/test_server_app_openai_segments.py index 06a4951f86..28df9bc6ed 100644 --- a/tests/test_server_app_openai_segments.py +++ b/tests/test_server_app_openai_segments.py @@ -12,6 +12,11 @@ SERVER_CLI_PATH = REPO_ROOT / "funasr" / "bin" / "server.py" +class PlainTextResponseStub: + def __init__(self, content=None): + self.content = content + + def load_server_app(monkeypatch): class DummyFastAPI: def __init__(self, *args, **kwargs): @@ -57,6 +62,7 @@ class DummyCORSMiddleware: responses_stub = types.ModuleType("fastapi.responses") responses_stub.JSONResponse = lambda content=None: content + responses_stub.PlainTextResponse = PlainTextResponseStub monkeypatch.setitem(sys.modules, "fastapi", fastapi_stub) monkeypatch.setitem(sys.modules, "fastapi.middleware", middleware_stub) @@ -260,6 +266,28 @@ def test_n8n_whisper_model_alias_uses_preloaded_model(monkeypatch): ] +def test_text_response_format_returns_plain_text(monkeypatch): + module = load_server_app(monkeypatch) + install_dummy_funasr(monkeypatch, generated_text='say "hi"') + monkeypatch.setattr(module.sf, "info", lambda path: types.SimpleNamespace(duration=1.25)) + app = module.create_app(device="cpu", preload_model="sensevoice") + transcribe = app.routes[("POST", "/v1/audio/transcriptions")] + + response = asyncio.run( + transcribe( + file=DummyUpload(), + model="sensevoice", + language=None, + response_format="text", + spk=False, + ) + ) + + # OpenAI returns the bare transcript, not a JSON-encoded string. + assert isinstance(response, PlainTextResponseStub) + assert response.content == 'say "hi"' + + def test_openai_verbose_json_preserves_speaker_labels(monkeypatch): module = load_server_app(monkeypatch) diff --git a/tests/test_timestamp_tools.py b/tests/test_timestamp_tools.py index a9dd41d18e..763c14e197 100644 --- a/tests/test_timestamp_tools.py +++ b/tests/test_timestamp_tools.py @@ -57,6 +57,31 @@ def test_timestamp_sentence_en_missing_trailing_timestamp_matches_zh_fallback(): assert en_result[1]["start"] == zh_result[1]["start"] +def test_timestamp_sentence_does_not_prefix_latin_text_with_a_space(): + mixed = timestamp_sentence( + punc_id_list=[1, 2, 1, 1, 3], + timestamp_postprocessed=[[0, 100], [100, 200], [200, 300], [300, 400], [400, 500]], + text_postprocessed="我 用 iphone pro max", + return_raw_text=True, + ) + assert [sentence["text"] for sentence in mixed] == ["我用,", "iphone pro max。"] + assert [sentence["raw_text"] for sentence in mixed] == ["我 用", "iphone pro max"] + + english = timestamp_sentence( + [1, 3, 1], + [[0, 100], [100, 200], [200, 300]], + "hello world again", + ) + assert [sentence["text"] for sentence in english] == ["hello world。", "again"] + + chinese = timestamp_sentence( + [1, 3], + [[0, 100], [100, 200]], + "你好 世界", + ) + assert chinese[0]["text"] == "你好世界。" + + def test_timestamp_sentence_raw_text_keeps_token_separators(): result = timestamp_sentence( punc_id_list=[1, 2, 1, 1, 3], diff --git a/tests/test_type_utils_compat.py b/tests/test_type_utils_compat.py new file mode 100644 index 0000000000..0be3cfbdac --- /dev/null +++ b/tests/test_type_utils_compat.py @@ -0,0 +1,65 @@ +"""Keep the command-line boolean parser compatible without distutils.""" +import importlib.util +from pathlib import Path +import subprocess +import sys + +import pytest + + +SOURCE = Path(__file__).resolve().parents[1] / "funasr/utils/type_utils.py" + + +@pytest.fixture(scope="module") +def parser(): + spec = importlib.util.spec_from_file_location("boolean_parser_under_test", SOURCE) + module = importlib.util.module_from_spec(spec) + spec.loader.exec_module(module) + return module.str2bool + + +@pytest.mark.parametrize( + ("value", "expected"), + [("y", True), ("yes", True), ("t", True), ("true", True), ("on", True), + ("1", True), ("n", False), ("no", False), ("f", False), ("false", False), + ("off", False), ("0", False), ("YeS", True), ("TRUE", True), + ("nO", False), ("OFF", False)], +) +def test_boolean_argument_preserves_values_and_boolean_type(parser, value, expected): + assert parser(value) is expected + + +@pytest.mark.parametrize( + ("value", "message"), + [("MAYBE", "invalid truth value 'maybe'"), + ("FaLsE!", "invalid truth value 'false!'"), + (" TRUE ", "invalid truth value ' true '"), + ("", "invalid truth value ''"), + ("2", "invalid truth value '2'"), + ("false!", "invalid truth value 'false!'")], +) +def test_invalid_boolean_argument_preserves_normalized_error(parser, value, message): + with pytest.raises(ValueError) as caught: + parser(value) + assert str(caught.value) == message + + +def test_boolean_parser_imports_when_distutils_is_unavailable(): + code = """ +import importlib.abc +import runpy +import sys + +class MissingDistutils(importlib.abc.MetaPathFinder): + def find_spec(self, fullname, path=None, target=None): + if fullname == 'distutils' or fullname.startswith('distutils.'): + raise ImportError('distutils is unavailable') + +sys.meta_path.insert(0, MissingDistutils()) +parse = runpy.run_path(sys.argv[1])['str2bool'] +assert parse('yes') is True +assert parse('no') is False +""" + result = subprocess.run([sys.executable, "-c", code, str(SOURCE)], + text=True, capture_output=True, timeout=20) + assert result.returncode == 0, result.stdout + result.stderr From 13520d65681845f408fcdb3ab4ce95820e8ab3fc Mon Sep 17 00:00:00 2001 From: zhifu gao Date: Fri, 13 Nov 2026 01:34:11 +0800 Subject: [PATCH 3/4] docs(http): distinguish pinned JSON recipes from current plain-text responses Correct the Product site CI failure exposed by #3874 without changing the handler or weakening security/format contracts. Preserve the 1.4.15 recipe and add visible, source-bound current-main notices. Signed-off-by: LauraGPT --- ...-hosted-deepgram-assemblyai-alternative.html | 3 ++- ...f-hosted-openai-whisper-api-alternative.html | 3 ++- ...-hosted-deepgram-assemblyai-alternative.html | 3 ++- ...f-hosted-openai-whisper-api-alternative.html | 3 ++- .../tests/test_http_blog_contracts.py | 17 +++++++++++++++-- 5 files changed, 23 insertions(+), 6 deletions(-) diff --git a/web-pages/product-site/legacy/blog/self-hosted-deepgram-assemblyai-alternative.html b/web-pages/product-site/legacy/blog/self-hosted-deepgram-assemblyai-alternative.html index 631379ae93..a92b9e038e 100644 --- a/web-pages/product-site/legacy/blog/self-hosted-deepgram-assemblyai-alternative.html +++ b/web-pages/product-site/legacy/blog/self-hosted-deepgram-assemblyai-alternative.html @@ -5,7 +5,7 @@