XCodec Mini Inference

XCodec Mini inference bundle containing the main codec, semantic encoder, decoder checkpoints, and local configuration/code required by the installed inference package.

Files and local identity

  • post_process_audio.py โ€” 5710 bytes; SHA-256 3f7acfe8936fe2b05c7f6357ba4988ad62d10e1f6f271d53f361c19a353ca002
  • vocoder.py โ€” 7394 bytes; SHA-256 719884412c9c43b5be1bea4b2c9cc871a9482bb0e91e634b79dbd70cab8f3e5e
  • decoders/config.yaml โ€” 269 bytes; SHA-256 5a0f1dd895d767ae5dd19323ba0f86fa15177d814e01f79edf9309ce164d5b0b
  • decoders/decoder_131000.pth โ€” 72611958 bytes; SHA-256 b99f0be84eeef3a32f29cd55beb89727fd0b2fd0df3dbad3023508f4c7185c37
  • decoders/decoder_151000.pth โ€” 72610550 bytes; SHA-256 8af97a29d3483f9d4a3755992837501bd7d6caa1a69382ed16e64039e0ea0998
  • descriptaudiocodec/dac/__init__.py โ€” 307 bytes; SHA-256 15575d30dc28e2ac6978b1c4f67b3b79a8e4198e1645ef7ccbfb2706b988b5fe
  • descriptaudiocodec/dac/__main__.py โ€” 666 bytes; SHA-256 94c3f738a79bdccaebfc1c92b015a46ddb9d9bbba1a41c29ef38d082b61dce6e
  • descriptaudiocodec/dac/compare/__init__.py โ€” 0 bytes; SHA-256 e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
  • descriptaudiocodec/dac/compare/encodec.py โ€” 1592 bytes; SHA-256 1d05139a912522dd7793142f1917914187d531f3c818635979841727ffbcf704
  • descriptaudiocodec/dac/model/__init__.py โ€” 117 bytes; SHA-256 19c5e09cc2236f7b32c3dcc4b8aaedf84e22bac100ddbd62fdd82b7bc702655b
  • descriptaudiocodec/dac/model/base.py โ€” 9384 bytes; SHA-256 2361726838faae352f1265d514e3e2f8d978a2b278dcf66bb5799dfbd2ba7b83
  • descriptaudiocodec/dac/model/dac.py โ€” 11216 bytes; SHA-256 a22f936c225161314b5569e0d4443a0f7ffaf261b27d949c2f6b72a23278a08e
  • descriptaudiocodec/dac/model/discriminator.py โ€” 7056 bytes; SHA-256 2fa20d5955c2402dc7ee204e1d86275074c475203b0ece97aafc934aab9ff6e1
  • descriptaudiocodec/dac/nn/__init__.py โ€” 63 bytes; SHA-256 9c3815860820bc1ef0e10c71140c90634b9eeef2bbf2a00445763ed4552c149a
  • descriptaudiocodec/dac/nn/layers.py โ€” 809 bytes; SHA-256 ec2649649d787b166a138d5ad9dcd585aeabbcd93670771b30cbbbab731c4b63
  • descriptaudiocodec/dac/nn/loss.py โ€” 12044 bytes; SHA-256 1e0b7d8bc9ef16a2f72f2c3b3f414d7bf7a05edb3391e9086406cf1dc44a35dc
  • descriptaudiocodec/dac/nn/quantize.py โ€” 9060 bytes; SHA-256 e2dc61f32f6123aa48a0aeb934a0d9a41ea29a5eae8db28119c791885c9f1b07
  • descriptaudiocodec/dac/utils/__init__.py โ€” 3290 bytes; SHA-256 ac4e097f5db5f730bdd944bfd7ddf66761e776ba22d14d5ad7e3d6bd902addf5
  • descriptaudiocodec/dac/utils/decode.py โ€” 2998 bytes; SHA-256 8b64cc408e25f5b2dbab01cf787d456552901e887a88c8aae53ee3f6832bab17
  • descriptaudiocodec/dac/utils/encode.py โ€” 3117 bytes; SHA-256 6052fd02ba78c37401c2b5087a8b50ea9e2be806975c317ba8534cdfc47f0f4c
  • final_ckpt/ckpt_00360000.pth โ€” 1360444883 bytes; SHA-256 c8c379ea2d3cbde1c8ba1b9717975220e79ba3f556bb161766fd5e4585dcd59c
  • final_ckpt/config.yaml โ€” 2863 bytes; SHA-256 35a3d0d553065844cc92dd4f972bf09af785ecdefc5921b117858a9c807c8680
  • models/__init__.py โ€” 0 bytes; SHA-256 e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
  • models/soundstream_hubert_new.py โ€” 8425 bytes; SHA-256 c56b0a60a9c181782fb9ea7e915c8eaf4cad5de960ed543bbaa39962d79f66b9
  • modules/__init__.py โ€” 525 bytes; SHA-256 df464b0516af77ae3f5ca79442e09d0f83592d6081e084f122a866581e84b0a8
  • modules/conv.py โ€” 10731 bytes; SHA-256 341602819df01a80123701b5d31485e40182ad49d017aac65eabc675e930aab5
  • modules/loss.py โ€” 5605 bytes; SHA-256 81235a838511fa9b1ab466e3aff826b39168c5b4deb5b968455da7f676743913
  • modules/lstm.py โ€” 782 bytes; SHA-256 53d0511f2eb17f2a3e7dbf0f3b969e05a9392aa0f986a3ea918840da58aaffc4
  • modules/norm.py โ€” 843 bytes; SHA-256 23d5727c362bfcd43ee8ba2972531b6b63991a974c11a9156b179134ce2c87d3
  • modules/seanet.py โ€” 12122 bytes; SHA-256 619a74c0a4c9fa59d9cbed748b2e430ea2fda746f984ee9b0957491b69dae483
  • modules/transformer.py โ€” 4598 bytes; SHA-256 2f15cafae83dd40c84c576c75e9a4b6f75f0e7ef101fe12cd65f661da944b83d
  • quantization/__init__.py โ€” 271 bytes; SHA-256 34c806bc1cafc8b835926b6f6450bee769f95eb467cf1c19b4427e9dd7e55bbc
  • quantization/core_vq_lsx_version.py โ€” 16050 bytes; SHA-256 154e2c5ddbacd3b82c74bf18d7177ea4b011cbd71e6e5575c7265b70e58c2af0
  • quantization/core_vq.py โ€” 13291 bytes; SHA-256 f1f1282e4fa63a9b0bff44309cd6cd9e0870d82470a26bdffcd2db9a6c93ae6f
  • quantization/distrib.py โ€” 4109 bytes; SHA-256 79b8dbfe3dda4da10ea0d3e143b373d90dd920f40d4a7f6f7446412b3584f655
  • quantization/vq.py โ€” 4598 bytes; SHA-256 8f24a4a389bad6dec6d77a35526264a1acd07c29a69854274bc73ebda4c622f9
  • RepCodec/.gitignore โ€” 3076 bytes; SHA-256 f7620e5e8920ca54dbb6f10a8b200e8c97d88630d16732ff6f7263ef213dc136
  • RepCodec/LICENSE โ€” 20452 bytes; SHA-256 3b606b937f137fcdbad4146ccc26369c9141eaad5f136d9347a0211af3babf1f
  • RepCodec/setup.py โ€” 883 bytes; SHA-256 802684f72757f134363fc4b8c9b90ea76a7e9cb9dda8bc62ef3e695b525ba13b
  • RepCodec/train.py โ€” 7713 bytes; SHA-256 33d7ef42471b241d8a8d5e144c7200bbd1b599cdcfbb20fa2188bc365aa86058
  • RepCodec/examples/data2vec_audio.py โ€” 18117 bytes; SHA-256 58ff990fcb4dcd343be8114fb06839abd9bb01bff9e44216fe2adeaa6ae5660b
  • RepCodec/examples/data2vec_feature_reader.py โ€” 3251 bytes; SHA-256 c7b3f66481ba9b5ffc596a605fd480cc1a75f557c11678019df91044f7ed3529
  • RepCodec/examples/dump_feature.py โ€” 3962 bytes; SHA-256 91198a662369d42049008598caed575c865ceecbb143b9e8d1172d4ee323ad6b
  • RepCodec/examples/feature_utils.py โ€” 2190 bytes; SHA-256 d275708011d3c26dee1084619bbdec4ec8bbe490352f3e88f50bdd9049a3ecf6
  • RepCodec/examples/hubert_feature_reader.py โ€” 2227 bytes; SHA-256 0a90b1926437f1c398772dade2780492888096d04488dc70d9f5a66e7af76231
  • RepCodec/examples/whisper_feature_reader.py โ€” 3867 bytes; SHA-256 dbf8981e7ee5831bba9307482823d13ab591fd912fe62b2214b3071f0d037aa9
  • RepCodec/examples/whisper_model.py โ€” 2020 bytes; SHA-256 19a6c76e5b84cabe46554c2d1174387b1c3b555b8d2d885a533f2be749d8730a
  • RepCodec/examples/tokens/data2vec_base_l6_dev-clean.tokens โ€” 3892241 bytes; SHA-256 9b75f98b89144639cb257559e704eac244e8c61f1b63a634aaf931ced3853f50
  • RepCodec/examples/tokens/data2vec_large_l18_dev-clean.tokens โ€” 3895002 bytes; SHA-256 61219d6012ec174f1c0ad37dcbeb962137617928d0006edd3f7ee8d80ab40e05
  • RepCodec/examples/tokens/hubert_base_l9_dev-clean.tokens โ€” 3879659 bytes; SHA-256 55a8c25efc6b5ad345e85b2143b9684179280e579a6a0c18a60475eee81d34b2
  • RepCodec/examples/tokens/hubert_large_l18_dev-clean.tokens โ€” 3886756 bytes; SHA-256 0594c6c139dc8b83c645d62d495b24787328a662666d901a010662cb9390b6d0
  • RepCodec/examples/tokens/whisper_large_l32_dev-clean.tokens โ€” 3830090 bytes; SHA-256 bbdc90e5415fa90ac5007fbf2e00884a0032e3a3cc6409ad225d2c8d9916784c
  • RepCodec/examples/tokens/whisper_medium_l24_dev-clean.tokens โ€” 3879911 bytes; SHA-256 c1f4bd40e0d44192a2fadb13ec43e103d0d0d3c94054760d8a8a2fb2e6dc8ff1
  • RepCodec/repcodec/RepCodec.py โ€” 2554 bytes; SHA-256 fbffa57152144c9002daa5a3d613ce0493b6c960f0c27bf818bb4f778985ff9b
  • RepCodec/repcodec/tokenize.py โ€” 6480 bytes; SHA-256 b1af49d0e21b90be5b3608543b060dadc4d751b7734af796e987aab35dcacebe
  • RepCodec/repcodec/configs/repcodec_dim1024.yaml โ€” 401 bytes; SHA-256 f499522b11f91feb69430cc701767c8f33650d9ed09e465a8e03669114f1782d
  • RepCodec/repcodec/configs/repcodec_dim1280.yaml โ€” 401 bytes; SHA-256 0a5f5056d08f3a87cd151cd8ddf45c9e3ffbaefa41de55fd614144ab5f160d31
  • RepCodec/repcodec/configs/repcodec_dim768.yaml โ€” 396 bytes; SHA-256 46b09e2cd5be996abe62f6a8701d8232868d63c75b60f31d1093cb00fcb5b009
  • RepCodec/repcodec/layers/conv_layer.py โ€” 2688 bytes; SHA-256 33d95a3a9e6e5e599d815b6a9acf56e1d49bf2447bfe2a112bdae6d593383b2b
  • RepCodec/repcodec/layers/vq_module.py โ€” 5764 bytes; SHA-256 ccae347595327b698207871076c77ca6afc0cb69f0d31fa08beeb6008e1af893
  • RepCodec/repcodec/modules/decoder.py โ€” 3397 bytes; SHA-256 871f898194689cae72260f6d560f9ea07a3e0c873932e16047483bd6862bcf22
  • RepCodec/repcodec/modules/encoder.py โ€” 2803 bytes; SHA-256 c706f53867cd309fbcc3ad95b0ef94f53f4f48252cfc9db7f7311b6698b03111
  • RepCodec/repcodec/modules/projector.py โ€” 816 bytes; SHA-256 819627eae168974c7447feeb2126634f357716237bcc1f8a64649772b06b1df6
  • RepCodec/repcodec/modules/quantizer.py โ€” 1302 bytes; SHA-256 1ef47d2efacb5345fe68270ea210f5388f01644964e845086120cbdfe6d26773
  • RepCodec/repcodec/modules/residual_unit.py โ€” 1210 bytes; SHA-256 e5c723aaca001ef4ea2c9e99eef687a95a8f1a1cb6c81d07995b77b91ad7695e
  • RepCodec/trainer/autoencoder.py โ€” 9471 bytes; SHA-256 86ba43ebe92053e61305fe3004815e6aefe87c013bb9d4a41e61f89b4e1d95ee
  • RepCodec/train_configs/ex_dim768_mse.yaml โ€” 2854 bytes; SHA-256 74020d52adba46a4bdeaf0cde6a3f2bdb81664dd5ca896dd4adc0e67c55edff4
  • semantic_ckpts/hf_1_325000/config.json โ€” 1375 bytes; SHA-256 94a146e3131d08618322bd6eed8aa0c41af3bb6a362f00d127854691b19348aa
  • semantic_ckpts/hf_1_325000/preprocessor_config.json โ€” 231 bytes; SHA-256 24b8799f94ab4e74fdb4369dea1e7c5fe51f98112033f432e1df892111e61d9f
  • semantic_ckpts/hf_1_325000/pytorch_model.bin โ€” 377555286 bytes; SHA-256 c5ddbd7fa2468483cb9b2aa53117813471543dd278e65870333a56c54305f527
  • utils/__init__.py โ€” 0 bytes; SHA-256 e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
  • utils/ddp_utils.py โ€” 9108 bytes; SHA-256 a53a4efc83ab34c8655d61bbcae7e0965a573ecce3321f8c1cffc2ec6889644f
  • utils/utils.py โ€” 8484 bytes; SHA-256 8521062c4b1afae1366a100244449a7dcdcc79883bf1874e50f9954c66c2ccd2
  • vocos/__init__.py โ€” 73 bytes; SHA-256 fb49e19176bff8f79b369ca3fc9c19326b00b330ff92bdf7e639eb747f7cea8f
  • vocos/dataset.py โ€” 2527 bytes; SHA-256 e718ef9e88c948024296613c32c55a24fffee14a808f18f8a2cfab53d53983f7
  • vocos/discriminators.py โ€” 8180 bytes; SHA-256 d61bd7fbbb87c6d576c10fd76c9c75c20bfe126bfd1749a3d63e0ed002f2cdf9
  • vocos/experiment.py โ€” 16741 bytes; SHA-256 09255db5ee2804e3389edf34d979d24a037e81240be67ecbbfb2178ebac790ef
  • vocos/feature_extractors.py โ€” 4917 bytes; SHA-256 b1d7e6270aaa79e03bea46eb845ef93aa4e9bfc850d58e5b9e445db5c1141752
  • vocos/heads.py โ€” 6699 bytes; SHA-256 b0c64dacad0147d19898b55366179c3fc527a59504bc1de65acfff732dd84703
  • vocos/helpers.py โ€” 1906 bytes; SHA-256 8d038968751dfe4c5d77121c7807214fa0db7acd3d399e06b740b5876a4d98b2
  • vocos/loss.py โ€” 4130 bytes; SHA-256 cef1f840e2e8410466fbce869c0394c0fece9a5a797e7475f305d78a9e2f93b9
  • vocos/models.py โ€” 5863 bytes; SHA-256 e3c0fab5439481f734ad2ce190c9f08b272c0df3cfe98fe1b85d07de3065b2c9
  • vocos/modules.py โ€” 7832 bytes; SHA-256 1132b0081333cc4abe1c36b2bd709185ceaa243519ea8903bec7ab08e67d5d64
  • vocos/pretrained.py โ€” 8533 bytes; SHA-256 79a160b6009a8c7f088cdd9ca87324a2f25d3cdf38cfba8c01a5803973fb7626
  • vocos/spectral_ops.py โ€” 8081 bytes; SHA-256 5577771daae83a9ffc6df3f1a3ce7f3f9c2543562c8ca3f5aff740ee2b515682

Upstream copies and provenance

License and use

License metadata follows the identified upstream license apache-2.0. Upstream terms and attribution requirements apply; this repository does not claim ownership of upstream model weights.

Provenance audit

Generated from local DMS model assets. Audit run: dms-model-assets-publish-20261022T0750Z-v7. SHA-256 values identify the local source bytes.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for DanielMarius/dms-xcodec-mini-infer

Finetuned
(1)
this model