Hugging Face's logo

Buckets:
hf-internal-testing
/
pocket-tts-integration-tests

Files
xet
hf-internal-testing/pocket-tts-integration-tests / single /metadata.json
eustlb's picture
eustlb
download
raw
8.57 kB
{
"case": "single",
"reference": {
"source": "https://github.com/kyutai-labs/pocket-tts",
"package": "pocket-tts",
"commit": "b94db177bc0f77517d9b124843e25605d6f9aed8",
"weights": "kyutai/pocket-tts (gated), pinned by revision in the package's configs"
},
"device": "NVIDIA A10G",
"torch_version": "2.14.0+cu130",
"dtype": "float32",
"precision_flags": "TF32 off (transformers conftest.py)",
"environment": {
"docker_image": "huggingface/transformers-all-latest-gpu@sha256:019c6e86a4b8a7e4439e2f2d72c995fe052e95292175238018254b8ea9c96fbe",
"gist_revision": "6268504309164b5bb9e26c39bae57fc139981825",
"pip_freeze": [
"absl-py==2.5.1",
"accelerate==1.16.0.dev0",
"aiohappyeyeballs==2.7.1",
"aiohttp==3.14.5",
"aiosignal==1.4.0",
"annotated-doc==0.0.5",
"annotated-types==0.8.0",
"antlr4-python3-runtime==4.9.3",
"anyio==4.15.1",
"attrs==26.1.0",
"audioread==3.1.0",
"av==18.1.0",
"beautifulsoup4==4.15.0",
"bitsandbytes==0.50.2",
"black==26.10.1",
"blobfile==3.1.0",
"certifi==2026.10.18",
"cffi==2.1.1",
"charset-normalizer==3.5.2",
"click==8.5.0",
"cloudpickle==3.1.2",
"contourpy==1.3.3",
"cryptography==50.0.2",
"cuda-bindings==13.4.4",
"cuda-pathfinder==1.8.3",
"cuda-toolkit==13.0.3.0",
"cycler==0.12.1",
"datasets==5.1.0",
"decorator==5.3.1",
"detectron2==0.6",
"diffusers==0.35.2",
"dill==0.4.1",
"Distance==0.1.3",
"dlinfo==2.0.0",
"dnspython==2.9.0",
"docopt==0.6.2",
"einops==0.8.2",
"email-validator==2.3.0",
"execnet==2.1.2",
"faiss-cpu==1.15.1",
"fastapi==0.146.0",
"fastjsonschema==2.22.2",
"filelock==4.2.3",
"flatbuffers==25.12.19",
"fonttools==4.67.0",
"frozenlist==1.8.0",
"fsspec==2026.7.0",
"fugashi==1.5.2",
"fvcore==0.1.5.post20221221",
"g2p-en==2.1.0",
"gitdb==4.0.12",
"GitPython==3.1.18",
"grpcio==1.84.0",
"h11==0.16.0",
"hf-doc-builder==0.5.0",
"hf-xet==1.7.0",
"httpcore2==2.14.0",
"httpx2==2.14.0",
"huggingface_hub==2.2.0",
"hydra-core==1.3.7",
"hypothesis==6.170.1",
"id==1.5.0",
"idna==3.20",
"importlib_metadata==9.0.1",
"inflect==7.5.0",
"iniconfig==2.3.1",
"iopath==0.1.9",
"ipadic==1.0.0",
"itsdangerous==2.0.1",
"Jinja2==3.1.6",
"jiter==0.17.0",
"joblib==1.6.0",
"jsonschema-specifications==2025.9.1",
"jsonschema==4.26.0",
"jupyter_core==5.9.1",
"kenlm==0.3.0",
"kiwisolver==1.5.1",
"lazy-loader==0.6",
"Levenshtein==0.27.5",
"libcst==1.9.0",
"librosa==0.11.0",
"llvmlite==0.50.0",
"lxml==6.1.3",
"markdown-it-py==4.2.0",
"Markdown==3.11.1",
"MarkupSafe==3.0.4",
"matplotlib==3.11.2",
"mdurl==0.1.2",
"mistral_common==1.12.0",
"ml_dtypes==0.6.0",
"more-itertools==11.2.1",
"mpmath==1.3.0",
"msgpack==1.2.3",
"multidict==7.1.0",
"multiprocess==0.70.19",
"mypy_extensions==1.1.0",
"narwhals==2.27.1",
"nbformat==5.11.1",
"networkx==3.6.1",
"nltk==3.8.1",
"num2words==0.5.14",
"numba==0.68.0",
"numpy==2.4.6",
"nvidia-cublas==13.1.1.3",
"nvidia-cuda-cupti==13.0.85",
"nvidia-cuda-nvrtc==13.0.88",
"nvidia-cuda-runtime==13.0.96",
"nvidia-cudnn-cu13==9.24.0.43",
"nvidia-cufft==12.0.0.61",
"nvidia-cufile==1.15.1.6",
"nvidia-curand==10.4.0.35",
"nvidia-cusolver==12.0.4.66",
"nvidia-cusparse==12.6.3.3",
"nvidia-cusparselt-cu13==0.8.1",
"nvidia-nccl-cu13==2.30.7",
"nvidia-nvjitlink==13.4.92",
"nvidia-nvshmem-cu13==3.4.5",
"nvidia-nvtx==13.0.85",
"omegaconf==2.3.1",
"onnx-ir==1.0.0",
"onnx==1.23.2",
"onnxruntime-gpu==1.31.0",
"onnxscript==0.7.2",
"openai==3.35.1",
"opencv-python-headless==4.11.0.86",
"opentelemetry-api==1.45.1",
"optimum==2.4.0.dev0",
"packaging==26.3",
"pandas==3.0.6",
"parameterized==0.9.0",
"pathspec==1.1.1",
"peft==0.21.3.dev0",
"phonemizer==3.4.0",
"pillow==13.0.0",
"pip==26.2.1",
"plac==1.4.7",
"platformdirs==4.13.5",
"pluggy==1.7.0",
"pocket-tts==3.3.0",
"pooch==1.9.0",
"portalocker==4.4.1",
"propcache==0.5.4",
"protobuf==7.36.2",
"psutil==7.2.2",
"pyarrow==26.0.0",
"pyasn1==0.6.4",
"pycocotools==2.0.11",
"pycountry==26.2.16",
"pycparser==3.11",
"pycryptodomex==3.24.1",
"pyctcdecode==0.5.0",
"pydantic-extra-types==2.11.1",
"pydantic==2.14.1",
"pydantic_core==2.50.1",
"Pygments==2.21.0",
"pygtrie==2.6.2",
"PyJWT==2.15.1",
"pyOpenSSL==26.4.0",
"pyparsing==3.3.3",
"pytesseract==0.3.13",
"pytest-asyncio==1.4.0",
"pytest-env==1.2.0",
"pytest-order==1.5.0",
"pytest-random-order==1.2.0",
"pytest-rerunfailures==15.1",
"pytest-rich==0.3.0",
"pytest-timeout==2.4.0",
"pytest-xdist==3.8.0",
"pytest==8.4.2",
"python-dateutil==2.9.0.post0",
"python-Levenshtein==0.27.5",
"python-multipart==0.0.32",
"pytokens==0.4.1",
"PyYAML==6.0.3",
"quanto==0.2.0",
"RapidFuzz==3.14.6",
"referencing==0.37.0",
"regex==2026.9.29",
"requests==2.34.2",
"rfc3161-client==1.0.9",
"rfc8785==0.1.4",
"rhoknp==1.3.0",
"rich==15.0.0",
"rjieba==0.2.1",
"rpds-py==2026.9.1",
"ruff==0.14.10",
"sacremoses==0.2.0",
"safetensors==0.8.0",
"scikit-learn==1.9.1",
"scipy==1.17.1",
"securesystemslib==1.5.1",
"sentencepiece==0.2.2",
"setuptools==84.0.0",
"shellingham==1.5.4",
"sigstore-models==0.0.6",
"sigstore-rekor-types==0.0.18",
"sigstore==4.5.0",
"six==1.17.0",
"smmap==5.0.3",
"sniffio==1.3.1",
"sortedcontainers==2.4.0",
"soundfile==0.14.0",
"soupsieve==3.0.3",
"soxr==1.1.0",
"starlette==1.9.0",
"sudachidict-core==20261015",
"SudachiPy==0.7.0",
"sympy==1.14.0",
"tabulate==0.10.0",
"tensorboard-data-server==0.7.2",
"tensorboard==2.21.0",
"termcolor==3.3.0",
"threadpoolctl==3.7.0",
"tiktoken==0.14.0",
"timeout-decorator==0.5.0",
"timm==1.0.30",
"tokenizers==0.23.3",
"tomli==2.5.0",
"tomlkit==0.15.2",
"torch==2.14.0+cu130",
"torchaudio==2.11.0+cu130",
"torchcodec==0.16.0+cpu",
"torchvision==0.29.1+cu130",
"tqdm==4.70.1",
"traitlets==5.16.1",
"transformers-mlinter==0.1.5",
"transformers==5.21.0.dev0",
"triton==3.8.0",
"truststore==0.10.5",
"tuf==7.0.0",
"ty==0.0.20",
"typeguard==4.6.0",
"typer==0.27.3",
"typing-inspection==0.4.4",
"typing_extensions==4.16.0",
"unidic-lite==1.0.8",
"unidic==1.1.0",
"urllib3==1.26.20",
"uvicorn==0.54.0",
"wasabi==0.10.1",
"Werkzeug==3.1.9",
"wheel==0.48.0",
"xxhash==4.0.1",
"yacs==0.1.8",
"yarl==1.25.1",
"zipp==4.1.1"
]
},
"inputs": {
"language": "english",
"text": "Hello world. I am Kyutai's Pocket TTS. I'm fast enough to run on small CPUs.",
"voice": "alba",
"do_sample": false
},
"prompt": {
"prepared_text": "Hello world. I am Kyutai's Pocket TTS. I'm fast enough to run on small CPUs.",
"token_ids": [
2994,
578,
263,
268,
686,
862,
327,
805,
1537,
264,
261,
1456,
603,
597,
602,
854,
640,
263,
268,
264,
283,
1420,
260,
747,
266,
791,
288,
860,
444,
759,
1917,
261,
263
],
"frames_after_eos": 3,
"max_gen_len": 163
},
"eos_threshold": -4.0,
"sanity": {
"num_samples": 130560,
"num_frames": 68,
"duration_s": 5.44,
"rms": 0.075732,
"peak": 0.488149,
"first_values": [
0.0,
3.32e-05,
0.0001243,
0.0002172
]
},
"shapes": {
"audio": [
130560
],
"audio_latents": [
68,
32
],
"eos_logits": [
68
]
}
}

Xet Storage Details

Size:
8.57 kB
·
Xet hash:
962a4a9e5413916cbe66aba98463cee6e890fce6c731e1fa864e672edc7d4e22

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.