From 070218d06977c30bec7a50a9eb66510dc07b6480 Mon Sep 17 00:00:00 2001 From: jiangjiawei <2893643245@qq.com> Date: Fri, 10 Jul 2026 16:41:29 +0800 Subject: [PATCH 1/2] fix: replace Korean text with Japanese in ja locale launchModel keys The launchModel section in ja.ts incorrectly contained Korean translations for modelName through noPackagesInstalled; restore proper Japanese strings. --- frontend/src/i18n/locales/ja.ts | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/frontend/src/i18n/locales/ja.ts b/frontend/src/i18n/locales/ja.ts index 32d022c307..bde9e528e0 100644 --- a/frontend/src/i18n/locales/ja.ts +++ b/frontend/src/i18n/locales/ja.ts @@ -72,21 +72,21 @@ const ja = { otherModel: 'その他モデル', confirmDeleteCustomModel: 'カスタムモデル {{modelName}} を削除しますか？この操作は元に戻せません。', - modelName: '모델 이름', - envPath: '환경 경로', - realPath: '실제 경로', - copyEnvPath: '환경 경로 복사', - viewPackages: '패키지 목록 보기', - installedPackages: '설치된 패키지', - packageName: '패키지 이름', - version: '버전', - location: '위치', - packagesCount: '패키지 수', - size: '크기', - pythonVersion: 'Python 버전', - createdAt: '생성 시간', - noVirtualEnvironmentsForNow: '현재 가상환경이 없습니다!', - noPackagesInstalled: '설치된 패키지가 없습니다', + modelName: 'モデル名', + envPath: '環境パス', + realPath: '実際のパス', + copyEnvPath: '環境パスをコピー', + viewPackages: 'パッケージ一覧を表示', + installedPackages: 'インストール済みパッケージ', + packageName: 'パッケージ名', + version: 'バージョン', + location: '場所', + packagesCount: 'パッケージ数', + size: 'サイズ', + pythonVersion: 'Python バージョン', + createdAt: '作成日時', + noVirtualEnvironmentsForNow: '現在、仮想環境はありません！', + noPackagesInstalled: 'インストールされたパッケージはありません', lastConfig: '最終設定', configCache: '設定キャッシュ', newCache: '新規キャッシュ', From 67b0802fc5406bc27ba1ada6bdbbbc2836f87bd8 Mon Sep 17 00:00:00 2001 From: jiangjiawei <2893643245@qq.com> Date: Fri, 10 Jul 2026 18:21:17 +0800 Subject: [PATCH 2/2] fix(model): add virtualenv packages for audio and video models Ensure all built-in audio and video models declare virtualenv dependencies so v2.0 default isolated launches install the required packages. --- xinference/model/audio/model_spec.json | 573 +++++++++++++++++++++++++ xinference/model/video/model_spec.json | 27 ++ 2 files changed, 600 insertions(+) diff --git a/xinference/model/audio/model_spec.json b/xinference/model/audio/model_spec.json index a2a66e07b8..a1f448e31a 100644 --- a/xinference/model/audio/model_spec.json +++ b/xinference/model/audio/model_spec.json @@ -7,6 +7,14 @@ "audio2text" ], "multilingual": true, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-tiny", @@ -24,6 +32,14 @@ "audio2text" ], "multilingual": false, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-tiny.en", @@ -41,6 +57,14 @@ "audio2text" ], "multilingual": true, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-base", @@ -58,6 +82,14 @@ "audio2text" ], "multilingual": false, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-base.en", @@ -75,6 +107,14 @@ "audio2text" ], "multilingual": true, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-small", @@ -92,6 +132,14 @@ "audio2text" ], "multilingual": false, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-small.en", @@ -109,6 +157,14 @@ "audio2text" ], "multilingual": true, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-medium", @@ -126,6 +182,14 @@ "audio2text" ], "multilingual": false, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-medium.en", @@ -143,6 +207,14 @@ "audio2text" ], "multilingual": true, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-large-v3", @@ -164,6 +236,14 @@ "audio2text" ], "multilingual": true, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "openai/whisper-large-v3-turbo", @@ -185,6 +265,14 @@ "audio2text" ], "multilingual": false, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "BELLE-2/Belle-distilwhisper-large-v2-zh", @@ -202,6 +290,14 @@ "audio2text" ], "multilingual": false, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "BELLE-2/Belle-whisper-large-v2-zh", @@ -219,6 +315,14 @@ "audio2text" ], "multilingual": false, + "virtualenv": { + "packages": [ + "transformers", + "accelerate", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "BELLE-2/Belle-whisper-large-v3-zh", @@ -241,6 +345,12 @@ ], "multilingual": true, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-tiny" @@ -258,6 +368,12 @@ ], "multilingual": false, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-tiny.en-mlx" @@ -275,6 +391,12 @@ ], "multilingual": true, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-base-mlx" @@ -292,6 +414,12 @@ ], "multilingual": false, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-base.en-mlx" @@ -309,6 +437,12 @@ ], "multilingual": true, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-small-mlx" @@ -326,6 +460,12 @@ ], "multilingual": false, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-small.en-mlx" @@ -343,6 +483,12 @@ ], "multilingual": true, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-medium-mlx" @@ -360,6 +506,12 @@ ], "multilingual": false, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-medium.en-mlx" @@ -377,6 +529,12 @@ ], "multilingual": true, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-large-v3-mlx" @@ -394,6 +552,12 @@ ], "multilingual": true, "engine": "mlx", + "virtualenv": { + "packages": [ + "mlx-whisper", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "mlx-community/whisper-large-v3-turbo" @@ -422,6 +586,14 @@ "merge_vad": true, "merge_length_s": 15 }, + "virtualenv": { + "packages": [ + "funasr==1.2.7", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "FunAudioLLM/SenseVoiceSmall", @@ -450,6 +622,14 @@ "default_transcription_config": { "batch_size_s": 300 }, + "virtualenv": { + "packages": [ + "funasr==1.2.7", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "funasr/paraformer-zh", @@ -479,6 +659,14 @@ "hotword": "", "batch_size_s": 300 }, + "virtualenv": { + "packages": [ + "funasr==1.2.7", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "JunHowie/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404", @@ -507,6 +695,14 @@ "default_transcription_config": { "batch_size_s": 300 }, + "virtualenv": { + "packages": [ + "funasr==1.2.7", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "JunHowie/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch", @@ -536,6 +732,14 @@ "default_transcription_config": { "batch_size_s": 300 }, + "virtualenv": { + "packages": [ + "funasr==1.2.7", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "JunHowie/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn", @@ -565,6 +769,14 @@ "hotword": "", "batch_size_s": 300 }, + "virtualenv": { + "packages": [ + "funasr==1.2.7", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "JunHowie/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", @@ -618,6 +830,26 @@ "text2audio_voice_cloning" ], "multilingual": true, + "virtualenv": { + "packages": [ + "librosa", + "tiktoken", + "lightning>=2.0.0", + "hydra-core>=1.3.2", + "inflect", + "conformer", + "diffusers==0.29.0", + "gdown", + "pyarrow", + "HyperPyYAML", + "onnxruntime>=1.16.0", + "pyworld>=0.3.4", + "wetext==0.0.9", + "transformers==4.51.3", + "#system_numpy#", + "#system_torch#" + ] + }, "model_src": { "huggingface": { "model_id": "FunAudioLLM/CosyVoice-300M", @@ -640,6 +872,26 @@ "text2audio_zero_shot" ], "multilingual": true, + "virtualenv": { + "packages": [ + "librosa", + "tiktoken", + "lightning>=2.0.0", + "hydra-core>=1.3.2", + "inflect", + "conformer", + "diffusers==0.29.0", + "gdown", + "pyarrow", + "HyperPyYAML", + "onnxruntime>=1.16.0", + "pyworld>=0.3.4", + "wetext==0.0.9", + "transformers==4.51.3", + "#system_numpy#", + "#system_torch#" + ] + }, "model_src": { "huggingface": { "model_id": "FunAudioLLM/CosyVoice-300M-SFT", @@ -662,6 +914,26 @@ "text2audio_zero_shot" ], "multilingual": true, + "virtualenv": { + "packages": [ + "librosa", + "tiktoken", + "lightning>=2.0.0", + "hydra-core>=1.3.2", + "inflect", + "conformer", + "diffusers==0.29.0", + "gdown", + "pyarrow", + "HyperPyYAML", + "onnxruntime>=1.16.0", + "pyworld>=0.3.4", + "wetext==0.0.9", + "transformers==4.51.3", + "#system_numpy#", + "#system_torch#" + ] + }, "model_src": { "huggingface": { "model_id": "FunAudioLLM/CosyVoice-300M-Instruct", @@ -728,6 +1000,27 @@ "text2audio_voice_cloning" ], "multilingual": true, + "virtualenv": { + "packages": [ + "loguru", + "natsort", + "loralib", + "ormsgpack", + "cachetools", + "silero-vad", + "vector-quantize-pytorch>=1.14.24,<=1.17.3", + "einops", + "lightning>=2.0.0", + "hydra-core>=1.3.2", + "omegaconf~=2.3.0", + "matplotlib", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "fishaudio/fish-speech-1.5", @@ -751,6 +1044,24 @@ "text2audio_voice_cloning" ], "multilingual": true, + "virtualenv": { + "packages": [ + "torchdiffeq", + "x_transformers>=1.31.14", + "pypinyin", + "tomli", + "vocos", + "librosa", + "jieba", + "pydub", + "soundfile", + "cached_path", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "SWivid/F5-TTS", @@ -774,6 +1085,15 @@ "text2audio_voice_cloning" ], "multilingual": true, + "virtualenv": { + "packages": [ + "f5-tts-mlx", + "vocos-mlx", + "soundfile", + "tomli", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "lucasnewman/f5-tts-mlx", @@ -793,6 +1113,33 @@ ], "multilingual": false, "language": "EN", + "virtualenv": { + "packages": [ + "cached_path", + "unidic-lite", + "cn2an", + "mecab-python3", + "num2words", + "pykakasi", + "fugashi", + "g2p_en", + "anyascii", + "gruut[de,es,fr]", + "g2pkk", + "jamo", + "jieba", + "pypinyin", + "nltk", + "inflect", + "six", + "librosa", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "myshell-ai/MeloTTS-English", @@ -812,6 +1159,33 @@ ], "multilingual": false, "language": "EN", + "virtualenv": { + "packages": [ + "cached_path", + "unidic-lite", + "cn2an", + "mecab-python3", + "num2words", + "pykakasi", + "fugashi", + "g2p_en", + "anyascii", + "gruut[de,es,fr]", + "g2pkk", + "jamo", + "jieba", + "pypinyin", + "nltk", + "inflect", + "six", + "librosa", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "myshell-ai/MeloTTS-English-v2", @@ -831,6 +1205,33 @@ ], "multilingual": false, "language": "EN", + "virtualenv": { + "packages": [ + "cached_path", + "unidic-lite", + "cn2an", + "mecab-python3", + "num2words", + "pykakasi", + "fugashi", + "g2p_en", + "anyascii", + "gruut[de,es,fr]", + "g2pkk", + "jamo", + "jieba", + "pypinyin", + "nltk", + "inflect", + "six", + "librosa", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "myshell-ai/MeloTTS-English-v3", @@ -850,6 +1251,33 @@ ], "multilingual": false, "language": "FR", + "virtualenv": { + "packages": [ + "cached_path", + "unidic-lite", + "cn2an", + "mecab-python3", + "num2words", + "pykakasi", + "fugashi", + "g2p_en", + "anyascii", + "gruut[de,es,fr]", + "g2pkk", + "jamo", + "jieba", + "pypinyin", + "nltk", + "inflect", + "six", + "librosa", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "myshell-ai/MeloTTS-French", @@ -869,6 +1297,33 @@ ], "multilingual": false, "language": "JP", + "virtualenv": { + "packages": [ + "cached_path", + "unidic-lite", + "cn2an", + "mecab-python3", + "num2words", + "pykakasi", + "fugashi", + "g2p_en", + "anyascii", + "gruut[de,es,fr]", + "g2pkk", + "jamo", + "jieba", + "pypinyin", + "nltk", + "inflect", + "six", + "librosa", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "myshell-ai/MeloTTS-Japanese", @@ -888,6 +1343,33 @@ ], "multilingual": false, "language": "ES", + "virtualenv": { + "packages": [ + "cached_path", + "unidic-lite", + "cn2an", + "mecab-python3", + "num2words", + "pykakasi", + "fugashi", + "g2p_en", + "anyascii", + "gruut[de,es,fr]", + "g2pkk", + "jamo", + "jieba", + "pypinyin", + "nltk", + "inflect", + "six", + "librosa", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "myshell-ai/MeloTTS-Spanish", @@ -907,6 +1389,33 @@ ], "multilingual": false, "language": "ZH", + "virtualenv": { + "packages": [ + "cached_path", + "unidic-lite", + "cn2an", + "mecab-python3", + "num2words", + "pykakasi", + "fugashi", + "g2p_en", + "anyascii", + "gruut[de,es,fr]", + "g2pkk", + "jamo", + "jieba", + "pypinyin", + "nltk", + "inflect", + "six", + "librosa", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "myshell-ai/MeloTTS-Chinese", @@ -926,6 +1435,33 @@ ], "multilingual": false, "language": "KR", + "virtualenv": { + "packages": [ + "cached_path", + "unidic-lite", + "cn2an", + "mecab-python3", + "num2words", + "pykakasi", + "fugashi", + "g2p_en", + "anyascii", + "gruut[de,es,fr]", + "g2pkk", + "jamo", + "jieba", + "pypinyin", + "nltk", + "inflect", + "six", + "librosa", + "soundfile", + "transformers", + "#system_torch#", + "#system_torchaudio#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "myshell-ai/MeloTTS-Korean", @@ -944,6 +1480,15 @@ "text2audio_zero_shot" ], "multilingual": true, + "virtualenv": { + "packages": [ + "kokoro>=0.7.15", + "misaki[en,zh]>=0.7.15", + "soundfile", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "hexgrad/Kokoro-82M" @@ -996,6 +1541,25 @@ "text2audio_zero_shot" ], "multilingual": true, + "virtualenv": { + "packages": [ + "WeTextProcessing", + "langdetect", + "pydub", + "pyloudnorm", + "librosa", + "einops", + "matplotlib", + "six", + "pyyaml", + "transformers", + "numba", + "more-itertools", + "tiktoken", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "ByteDance/MegaTTS3", @@ -1018,6 +1582,15 @@ "text2audio_zero_shot" ], "multilingual": false, + "virtualenv": { + "packages": [ + "kokoro>=0.7.15", + "misaki[en,zh]>=0.7.15", + "soundfile", + "#system_torch#", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "hexgrad/Kokoro-82M-v1.1-zh" diff --git a/xinference/model/video/model_spec.json b/xinference/model/video/model_spec.json index 97b4a4b7e7..fcb8acd132 100644 --- a/xinference/model/video/model_spec.json +++ b/xinference/model/video/model_spec.json @@ -13,6 +13,15 @@ "default_generate_config": { "guidance_scale": 6 }, + "virtualenv": { + "packages": [ + "diffusers>=0.33.0", + "ftfy", + "imageio-ffmpeg", + "imageio", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "THUDM/CogVideoX-2b", @@ -40,6 +49,15 @@ "default_generate_config": { "guidance_scale": 7 }, + "virtualenv": { + "packages": [ + "diffusers>=0.33.0", + "ftfy", + "imageio-ffmpeg", + "imageio", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "THUDM/CogVideoX-5b", @@ -65,6 +83,15 @@ "torch_dtype": "float16" }, "default_generate_config": {}, + "virtualenv": { + "packages": [ + "diffusers>=0.33.0", + "ftfy", + "imageio-ffmpeg", + "imageio", + "#system_numpy#" + ] + }, "model_src": { "huggingface": { "model_id": "hunyuanvideo-community/HunyuanVideo",