niobures/Step-Audio
By niobures · ↓ 0 · ♥ 0 · Updated 2025-11-29
What's in this repo
This page lists the files in niobures/Step-Audio, including campplus.onnx, speech_tokenizer_v2_25hz.onnx, speech_tokenizer_v1.onnx and more.
- 17 ONNX models (.onnx files)
- 763 files, including 346 .py, 111 .json, 83 .safetensors, 33 .txt, 28 .yaml, 23 .md
- Last updated 2025-11-29
ONNX files
| File | Size | Download |
|---|---|---|
| models/Step-Audio-2-mini-Base/token2wav/campplus.onnx | — | Download |
| models/Step-Audio-2-mini-Base/token2wav/speech_tokenizer_v2_25hz.onnx | — | Download |
| models/Step-Audio-2-mini-Think/token2wav/campplus.onnx | — | Download |
| models/Step-Audio-2-mini-Think/token2wav/speech_tokenizer_v2_25hz.onnx | — | Download |
| models/Step-Audio-2-mini-fork/token2wav/campplus.onnx | — | Download |
| models/Step-Audio-2-mini-fork/token2wav/speech_tokenizer_v2_25hz.onnx | — | Download |
| models/Step-Audio-2-mini/token2wav/campplus.onnx | — | Download |
| models/Step-Audio-2-mini/token2wav/speech_tokenizer_v2_25hz.onnx | — | Download |
| models/Step-Audio-EditX-bnb-4bit/CosyVoice-300M-25Hz/campplus.onnx | — | Download |
| models/Step-Audio-EditX-bnb-4bit/CosyVoice-300M-25Hz/speech_tokenizer_v1.onnx | — | Download |
Showing 10 of 17 .onnx files — see the full file list on the right.
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
No README provided by the author.
Model info
onnx
safetensors
region:us
↓ 0
♥ 0
Created: 2025-11-06
Updated: 2025-11-29
View on Hugging FaceFiles (763)
.gitattributes
Step-Audio-AQAA. A Fully End-to-End Expressive Large Audio Language Model.pdf
Step-Audio-EditX Technical Report.pdf
Step-Audio. Unified Understanding and Generation in Intelligent Speech Interaction.pdf
code/ComfyUI_StepAudioTTS.zip
code/Step-Audio [intervitens].zip
code/Step-Audio-EditX.zip
code/Step-Audio-tts.zip
code/Step-Audio.zip
code/Step-Audio2.zip
code/StepAudioInfer.zip
code/astrbot_plugin_tts_Step_Audio.zip
dataset/StepEval-Audio-360/.gitattributes
dataset/StepEval-Audio-360/README.md
dataset/StepEval-Audio-360/audios.tar.gz
dataset/StepEval-Audio-360/data/test-00000-of-00001.parquet
dataset/StepEval-Audio-360/source.txt
demo/Step-Audio-EditX/.gitattributes
demo/Step-Audio-EditX/.gitignore
demo/Step-Audio-EditX/LICENSE
demo/Step-Audio-EditX/README.md
demo/Step-Audio-EditX/__init__.py
demo/Step-Audio-EditX/app.py
demo/Step-Audio-EditX/config/__init__.py
demo/Step-Audio-EditX/config/edit_config.py
demo/Step-Audio-EditX/config/prompts.py
demo/Step-Audio-EditX/funasr_detach/__init__.py
demo/Step-Audio-EditX/funasr_detach/auto/__init__.py
demo/Step-Audio-EditX/funasr_detach/auto/auto_frontend.py
demo/Step-Audio-EditX/funasr_detach/auto/auto_model.py
demo/Step-Audio-EditX/funasr_detach/auto/auto_tokenizer.py
demo/Step-Audio-EditX/funasr_detach/bin/__init__.py
demo/Step-Audio-EditX/funasr_detach/bin/compute_audio_cmvn.py
demo/Step-Audio-EditX/funasr_detach/bin/inference.py
demo/Step-Audio-EditX/funasr_detach/bin/tokenize_text.py
demo/Step-Audio-EditX/funasr_detach/bin/train.py
demo/Step-Audio-EditX/funasr_detach/datasets/__init__.py
demo/Step-Audio-EditX/funasr_detach/datasets/audio_datasets/__init__.py
demo/Step-Audio-EditX/funasr_detach/datasets/audio_datasets/datasets.py
demo/Step-Audio-EditX/funasr_detach/datasets/audio_datasets/index_ds.py
demo/Step-Audio-EditX/funasr_detach/datasets/audio_datasets/preprocessor.py
demo/Step-Audio-EditX/funasr_detach/datasets/audio_datasets/samplers.py
demo/Step-Audio-EditX/funasr_detach/datasets/audio_datasets/scp2jsonl.py
demo/Step-Audio-EditX/funasr_detach/download/__init__.py
demo/Step-Audio-EditX/funasr_detach/download/download_dataset_from_hub.py
demo/Step-Audio-EditX/funasr_detach/download/download_from_hub.py
demo/Step-Audio-EditX/funasr_detach/download/file.py
demo/Step-Audio-EditX/funasr_detach/download/name_maps_from_hub.py
demo/Step-Audio-EditX/funasr_detach/download/runtime_sdk_download_tool.py
demo/Step-Audio-EditX/funasr_detach/frontends/__init__.py
demo/Step-Audio-EditX/funasr_detach/frontends/default.py
demo/Step-Audio-EditX/funasr_detach/frontends/eend_ola_feature.py
demo/Step-Audio-EditX/funasr_detach/frontends/fused.py
demo/Step-Audio-EditX/funasr_detach/frontends/s3prl.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/__init__.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/beamformer.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/complex_utils.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/dnn_beamformer.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/dnn_wpe.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/feature_transform.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/frontend.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/log_mel.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/mask_estimator.py
demo/Step-Audio-EditX/funasr_detach/frontends/utils/stft.py
demo/Step-Audio-EditX/funasr_detach/frontends/wav_frontend.py
demo/Step-Audio-EditX/funasr_detach/frontends/windowing.py
demo/Step-Audio-EditX/funasr_detach/losses/__init__.py
demo/Step-Audio-EditX/funasr_detach/losses/label_smoothing_loss.py
demo/Step-Audio-EditX/funasr_detach/metrics/__init__.py
demo/Step-Audio-EditX/funasr_detach/metrics/common.py
demo/Step-Audio-EditX/funasr_detach/metrics/compute_acc.py
demo/Step-Audio-EditX/funasr_detach/metrics/compute_eer.py
demo/Step-Audio-EditX/funasr_detach/metrics/compute_min_dcf.py
demo/Step-Audio-EditX/funasr_detach/metrics/compute_wer.py
demo/Step-Audio-EditX/funasr_detach/models/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/bat/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/bat/model.py
demo/Step-Audio-EditX/funasr_detach/models/bicif_paraformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/bicif_paraformer/cif_predictor.py
demo/Step-Audio-EditX/funasr_detach/models/bicif_paraformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/bicif_paraformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/branchformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/branchformer/cgmlp.py
demo/Step-Audio-EditX/funasr_detach/models/branchformer/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/branchformer/fastformer.py
demo/Step-Audio-EditX/funasr_detach/models/branchformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/branchformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/campplus/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/campplus/cluster_backend.py
demo/Step-Audio-EditX/funasr_detach/models/campplus/components.py
demo/Step-Audio-EditX/funasr_detach/models/campplus/model.py
demo/Step-Audio-EditX/funasr_detach/models/campplus/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/campplus/utils.py
demo/Step-Audio-EditX/funasr_detach/models/conformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/conformer/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/conformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/conformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/contextual_paraformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/contextual_paraformer/decoder.py
demo/Step-Audio-EditX/funasr_detach/models/contextual_paraformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/contextual_paraformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer/utils.py
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer_streaming/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer_streaming/attention.py
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer_streaming/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer_streaming/model.py
demo/Step-Audio-EditX/funasr_detach/models/ct_transformer_streaming/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/ctc/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/ctc/ctc.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/data2vec.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/data2vec_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/data_utils.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/ema_module.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/grad_multiply.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/multihead_attention.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/quant_noise.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/utils.py
demo/Step-Audio-EditX/funasr_detach/models/data2vec/wav2vec2.py
demo/Step-Audio-EditX/funasr_detach/models/e_branchformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/e_branchformer/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/e_branchformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/e_branchformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/eend/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/eend/e2e_diar_eend_ola.py
demo/Step-Audio-EditX/funasr_detach/models/eend/eend_ola_dataloader.py
demo/Step-Audio-EditX/funasr_detach/models/eend/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/eend/encoder_decoder_attractor.py
demo/Step-Audio-EditX/funasr_detach/models/eend/utils/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/eend/utils/feature.py
demo/Step-Audio-EditX/funasr_detach/models/eend/utils/kaldi_data.py
demo/Step-Audio-EditX/funasr_detach/models/eend/utils/losses.py
demo/Step-Audio-EditX/funasr_detach/models/eend/utils/power.py
demo/Step-Audio-EditX/funasr_detach/models/eend/utils/report.py
demo/Step-Audio-EditX/funasr_detach/models/emotion2vec/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/emotion2vec/audio.py
demo/Step-Audio-EditX/funasr_detach/models/emotion2vec/base.py
demo/Step-Audio-EditX/funasr_detach/models/emotion2vec/fairseq_modules.py
demo/Step-Audio-EditX/funasr_detach/models/emotion2vec/model.py
demo/Step-Audio-EditX/funasr_detach/models/emotion2vec/modules.py
demo/Step-Audio-EditX/funasr_detach/models/emotion2vec/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/emotion2vec/timm_modules.py
demo/Step-Audio-EditX/funasr_detach/models/eres2net/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/eres2net/eres2net.py
demo/Step-Audio-EditX/funasr_detach/models/eres2net/eres2net_aug.py
demo/Step-Audio-EditX/funasr_detach/models/eres2net/fusion.py
demo/Step-Audio-EditX/funasr_detach/models/fsmn_vad_streaming/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/fsmn_vad_streaming/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/fsmn_vad_streaming/model.py
demo/Step-Audio-EditX/funasr_detach/models/fsmn_vad_streaming/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/language_model/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/language_model/rnn/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/language_model/rnn/argument.py
demo/Step-Audio-EditX/funasr_detach/models/language_model/rnn/attentions.py
demo/Step-Audio-EditX/funasr_detach/models/language_model/rnn/decoders.py
demo/Step-Audio-EditX/funasr_detach/models/language_model/rnn/encoders.py
demo/Step-Audio-EditX/funasr_detach/models/language_model/seq_rnn_lm.py
demo/Step-Audio-EditX/funasr_detach/models/language_model/transformer_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/language_model/transformer_lm.py
demo/Step-Audio-EditX/funasr_detach/models/lora/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/lora/layers.py
demo/Step-Audio-EditX/funasr_detach/models/lora/utils.py
demo/Step-Audio-EditX/funasr_detach/models/mfcca/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/mfcca/e2e_asr_mfcca.py
demo/Step-Audio-EditX/funasr_detach/models/mfcca/encoder_layer_mfcca.py
demo/Step-Audio-EditX/funasr_detach/models/mfcca/mfcca_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/model_hf/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/monotonic_aligner/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/monotonic_aligner/model.py
demo/Step-Audio-EditX/funasr_detach/models/monotonic_aligner/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/mossformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/mossformer/e2e_ss.py
demo/Step-Audio-EditX/funasr_detach/models/mossformer/mossformer.py
demo/Step-Audio-EditX/funasr_detach/models/mossformer/mossformer_decoder.py
demo/Step-Audio-EditX/funasr_detach/models/mossformer/mossformer_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/normalize/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/normalize/global_mvn.py
demo/Step-Audio-EditX/funasr_detach/models/normalize/utterance_mvn.py
demo/Step-Audio-EditX/funasr_detach/models/paraformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/paraformer/cif_predictor.py
demo/Step-Audio-EditX/funasr_detach/models/paraformer/decoder.py
demo/Step-Audio-EditX/funasr_detach/models/paraformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/paraformer/search.py
demo/Step-Audio-EditX/funasr_detach/models/paraformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/paraformer_streaming/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/paraformer_streaming/model.py
demo/Step-Audio-EditX/funasr_detach/models/paraformer_streaming/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/cuda_decoder/wkv_cuda.cu
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/cuda_decoder/wkv_op.cpp
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/cuda_encoder/wkv_cuda.cu
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/cuda_encoder/wkv_op.cpp
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/rwkv.py
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/rwkv_attention.py
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/rwkv_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/rwkv_feed_forward.py
demo/Step-Audio-EditX/funasr_detach/models/rwkv_bat/rwkv_subsampling.py
demo/Step-Audio-EditX/funasr_detach/models/sa_asr/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/sa_asr/attention.py
demo/Step-Audio-EditX/funasr_detach/models/sa_asr/beam_search_sa_asr.py
demo/Step-Audio-EditX/funasr_detach/models/sa_asr/e2e_sa_asr.py
demo/Step-Audio-EditX/funasr_detach/models/sa_asr/transformer_decoder.py
demo/Step-Audio-EditX/funasr_detach/models/sanm/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/sanm/attention.py
demo/Step-Audio-EditX/funasr_detach/models/sanm/decoder.py
demo/Step-Audio-EditX/funasr_detach/models/sanm/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/sanm/model.py
demo/Step-Audio-EditX/funasr_detach/models/sanm/positionwise_feed_forward.py
demo/Step-Audio-EditX/funasr_detach/models/sanm/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/scama/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/scama/beam_search.py
demo/Step-Audio-EditX/funasr_detach/models/scama/chunk_utilis.py
demo/Step-Audio-EditX/funasr_detach/models/scama/decoder.py
demo/Step-Audio-EditX/funasr_detach/models/scama/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/scama/model.py
demo/Step-Audio-EditX/funasr_detach/models/scama/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/scama/utils.py
demo/Step-Audio-EditX/funasr_detach/models/seaco_paraformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/seaco_paraformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/seaco_paraformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/sond/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/sond/attention.py
demo/Step-Audio-EditX/funasr_detach/models/sond/e2e_diar_sond.py
demo/Step-Audio-EditX/funasr_detach/models/sond/encoder/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/sond/encoder/ci_scorers.py
demo/Step-Audio-EditX/funasr_detach/models/sond/encoder/conv_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/sond/encoder/ecapa_tdnn_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/sond/encoder/fsmn_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/sond/encoder/resnet34_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/sond/encoder/self_attention_encoder.py
demo/Step-Audio-EditX/funasr_detach/models/sond/label_aggregation.py
demo/Step-Audio-EditX/funasr_detach/models/sond/pooling/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/sond/pooling/pooling_layers.py
demo/Step-Audio-EditX/funasr_detach/models/sond/pooling/statistic_pooling.py
demo/Step-Audio-EditX/funasr_detach/models/sond/sv_decoder.py
demo/Step-Audio-EditX/funasr_detach/models/specaug/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/specaug/mask_along_axis.py
demo/Step-Audio-EditX/funasr_detach/models/specaug/profileaug.py
demo/Step-Audio-EditX/funasr_detach/models/specaug/specaug.py
demo/Step-Audio-EditX/funasr_detach/models/specaug/time_warp.py
demo/Step-Audio-EditX/funasr_detach/models/transducer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/transducer/beam_search_transducer.py
demo/Step-Audio-EditX/funasr_detach/models/transducer/joint_network.py
demo/Step-Audio-EditX/funasr_detach/models/transducer/model.py
demo/Step-Audio-EditX/funasr_detach/models/transducer/rnn_decoder.py
demo/Step-Audio-EditX/funasr_detach/models/transducer/rnnt_decoder.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/attention.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/decoder.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/embedding.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/encoder.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/layer_norm.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/model.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/positionwise_feed_forward.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/scorers/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/scorers/ctc.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/scorers/ctc_prefix_score.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/scorers/length_bonus.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/scorers/scorer_interface.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/search.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/add_sos_eos.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/dynamic_conv.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/dynamic_conv2d.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/lightconv.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/lightconv2d.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/mask.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/multi_layer_conv.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/nets_utils.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/repeat.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/subsampling.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/subsampling_without_posenc.py
demo/Step-Audio-EditX/funasr_detach/models/transformer/utils/vgg2l.py
demo/Step-Audio-EditX/funasr_detach/models/uniasr/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/uniasr/beam_search.py
demo/Step-Audio-EditX/funasr_detach/models/uniasr/model.py
demo/Step-Audio-EditX/funasr_detach/models/uniasr/template.yaml
demo/Step-Audio-EditX/funasr_detach/models/whisper/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/whisper/model.py
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/gpt2/merges.txt
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/gpt2/special_tokens_map.json
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/gpt2/tokenizer_config.json
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/gpt2/vocab.json
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/mel_filters.npz
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/multilingual/added_tokens.json
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/multilingual/merges.txt
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/multilingual/special_tokens_map.json
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/multilingual/tokenizer_config.json
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/assets/multilingual/vocab.json
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/audio.py
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/decoding.py
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/tokenizer.py
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/transcribe.py
demo/Step-Audio-EditX/funasr_detach/models/whisper/utils/utils.py
demo/Step-Audio-EditX/funasr_detach/models/xvector/__init__.py
demo/Step-Audio-EditX/funasr_detach/models/xvector/e2e_sv.py
demo/Step-Audio-EditX/funasr_detach/optimizers/__init__.py
demo/Step-Audio-EditX/funasr_detach/optimizers/fairseq_adam.py
demo/Step-Audio-EditX/funasr_detach/optimizers/sgd.py
demo/Step-Audio-EditX/funasr_detach/register.py
demo/Step-Audio-EditX/funasr_detach/schedulers/__init__.py
demo/Step-Audio-EditX/funasr_detach/schedulers/abs_scheduler.py
demo/Step-Audio-EditX/funasr_detach/schedulers/noam_lr.py
demo/Step-Audio-EditX/funasr_detach/schedulers/tri_stage_scheduler.py
demo/Step-Audio-EditX/funasr_detach/schedulers/warmup_lr.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/__init__.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/abs_tokenizer.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/build_tokenizer.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/char_tokenizer.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/cleaner.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/korean_cleaner.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/phoneme_tokenizer.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/sentencepiece_tokenizer.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/token_id_converter.py
demo/Step-Audio-EditX/funasr_detach/tokenizer/word_tokenizer.py
demo/Step-Audio-EditX/funasr_detach/train_utils/__init__.py
demo/Step-Audio-EditX/funasr_detach/train_utils/add_gradient_noise.py
demo/Step-Audio-EditX/funasr_detach/train_utils/average_nbest_models.py
demo/Step-Audio-EditX/funasr_detach/train_utils/device_funcs.py
demo/Step-Audio-EditX/funasr_detach/train_utils/forward_adaptor.py
demo/Step-Audio-EditX/funasr_detach/train_utils/initialize.py
demo/Step-Audio-EditX/funasr_detach/train_utils/load_pretrained_model.py
demo/Step-Audio-EditX/funasr_detach/train_utils/model_summary.py
demo/Step-Audio-EditX/funasr_detach/train_utils/recursive_op.py
demo/Step-Audio-EditX/funasr_detach/train_utils/set_all_random_seed.py
demo/Step-Audio-EditX/funasr_detach/train_utils/trainer.py
demo/Step-Audio-EditX/funasr_detach/utils/__init__.py
demo/Step-Audio-EditX/funasr_detach/utils/datadir_writer.py
demo/Step-Audio-EditX/funasr_detach/utils/load_utils.py
demo/Step-Audio-EditX/funasr_detach/utils/misc.py
demo/Step-Audio-EditX/funasr_detach/utils/postprocess_utils.py
demo/Step-Audio-EditX/funasr_detach/utils/prepare_data.py
demo/Step-Audio-EditX/funasr_detach/utils/speaker_utils.py
demo/Step-Audio-EditX/funasr_detach/utils/timestamp_tools.py
demo/Step-Audio-EditX/funasr_detach/utils/types.py
demo/Step-Audio-EditX/funasr_detach/utils/vad_utils.py
demo/Step-Audio-EditX/funasr_detach/version.txt
demo/Step-Audio-EditX/model_loader.py
demo/Step-Audio-EditX/requirements.txt
demo/Step-Audio-EditX/source.txt
demo/Step-Audio-EditX/stepvocoder/__init__.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/activations.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/cuda/__init__.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/cuda/activation1d.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/cuda/anti_alias_activation.cpp
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/cuda/anti_alias_activation_cuda.cu
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/cuda/compat.h
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/cuda/load.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/cuda/type_shim.h
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/torch/__init__.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/torch/act.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/torch/filter.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/alias_free_activation/torch/resample.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/bigvgan.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/bigvgan/bigvgan_utils.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/cli/cosyvoice.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/cli/frontend.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/embedding/__init__.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/embedding/dual_codebook.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/flow/__init__.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/flow/decoder_dit.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/flow/flow.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/flow/flow_matching.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/hifigan/__init__.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/hifigan/activation.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/hifigan/f0_predictor.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/hifigan/generator.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/matcha/audio.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/transformer/__init__.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/transformer/attention.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/transformer/embedding.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/transformer/encoder_layer.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/transformer/positionwise_feed_forward.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/transformer/subsampling.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/transformer/upsample_encoder_v2.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/utils/class_utils.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/utils/common.py
demo/Step-Audio-EditX/stepvocoder/cosyvoice2/utils/mask.py
demo/Step-Audio-EditX/tokenizer.py
demo/Step-Audio-EditX/tts.py
demo/Step-Audio-EditX/utils.py
models/Step-Audio-2-mini-Base/.gitattributes
models/Step-Audio-2-mini-Base/README.md
models/Step-Audio-2-mini-Base/added_tokens.json
models/Step-Audio-2-mini-Base/assets/architecture5.png
models/Step-Audio-2-mini-Base/assets/arxiv.svg
models/Step-Audio-2-mini-Base/assets/logo.png
models/Step-Audio-2-mini-Base/assets/qrcode.jpg
models/Step-Audio-2-mini-Base/assets/radar.png
models/Step-Audio-2-mini-Base/assets/wechat_group.png
models/Step-Audio-2-mini-Base/config.json
models/Step-Audio-2-mini-Base/configuration_step_audio_2.py
models/Step-Audio-2-mini-Base/merges.txt
models/Step-Audio-2-mini-Base/model-00001.safetensors
models/Step-Audio-2-mini-Base/model-00002.safetensors
models/Step-Audio-2-mini-Base/model.safetensors.index.json
models/Step-Audio-2-mini-Base/modeling_step_audio_2.py
models/Step-Audio-2-mini-Base/source.txt
models/Step-Audio-2-mini-Base/special_tokens_map.json
models/Step-Audio-2-mini-Base/token2wav/campplus.onnx
ONNX
models/Step-Audio-2-mini-Base/token2wav/flow.pt
models/Step-Audio-2-mini-Base/token2wav/flow.yaml
models/Step-Audio-2-mini-Base/token2wav/hift.pt
models/Step-Audio-2-mini-Base/token2wav/speech_tokenizer_v2_25hz.onnx
ONNX
models/Step-Audio-2-mini-Base/tokenizer.json
models/Step-Audio-2-mini-Base/tokenizer_config.json
models/Step-Audio-2-mini-Base/vocab.json
models/Step-Audio-2-mini-Think/.gitattributes
models/Step-Audio-2-mini-Think/README.md
models/Step-Audio-2-mini-Think/added_tokens.json
models/Step-Audio-2-mini-Think/assets/architecture5.png
models/Step-Audio-2-mini-Think/assets/arxiv.svg
models/Step-Audio-2-mini-Think/assets/logo.png
models/Step-Audio-2-mini-Think/assets/qrcode.jpg
models/Step-Audio-2-mini-Think/assets/radar.png
models/Step-Audio-2-mini-Think/assets/wechat_group.png
models/Step-Audio-2-mini-Think/config.json
models/Step-Audio-2-mini-Think/configuration_step_audio_2.py
models/Step-Audio-2-mini-Think/merges.txt
models/Step-Audio-2-mini-Think/model-00001.safetensors
models/Step-Audio-2-mini-Think/model-00002.safetensors
models/Step-Audio-2-mini-Think/model.safetensors.index.json
models/Step-Audio-2-mini-Think/modeling_step_audio_2.py
models/Step-Audio-2-mini-Think/source.txt
models/Step-Audio-2-mini-Think/special_tokens_map.json
models/Step-Audio-2-mini-Think/token2wav/campplus.onnx
ONNX
models/Step-Audio-2-mini-Think/token2wav/flow.pt
models/Step-Audio-2-mini-Think/token2wav/flow.yaml
models/Step-Audio-2-mini-Think/token2wav/hift.pt
models/Step-Audio-2-mini-Think/token2wav/speech_tokenizer_v2_25hz.onnx
ONNX
models/Step-Audio-2-mini-Think/tokenizer.json
models/Step-Audio-2-mini-Think/tokenizer_config.json
models/Step-Audio-2-mini-Think/vocab.json
models/Step-Audio-2-mini-fork/.gitattributes
models/Step-Audio-2-mini-fork/README.md
models/Step-Audio-2-mini-fork/added_tokens.json
models/Step-Audio-2-mini-fork/assets/architecture5.png
models/Step-Audio-2-mini-fork/assets/arxiv.svg
models/Step-Audio-2-mini-fork/assets/logo.png
models/Step-Audio-2-mini-fork/assets/qrcode.jpg
models/Step-Audio-2-mini-fork/assets/radar.png
models/Step-Audio-2-mini-fork/assets/wechat_group.png
models/Step-Audio-2-mini-fork/config.json
models/Step-Audio-2-mini-fork/configuration_step_audio_2.py
models/Step-Audio-2-mini-fork/merges.txt
models/Step-Audio-2-mini-fork/model-00001-of-00004.safetensors
models/Step-Audio-2-mini-fork/model-00002-of-00004.safetensors
models/Step-Audio-2-mini-fork/model-00003-of-00004.safetensors
models/Step-Audio-2-mini-fork/model-00004-of-00004.safetensors
models/Step-Audio-2-mini-fork/model.safetensors.index.json
models/Step-Audio-2-mini-fork/modeling_step_audio_2.py
models/Step-Audio-2-mini-fork/source.txt
models/Step-Audio-2-mini-fork/special_tokens_map.json
models/Step-Audio-2-mini-fork/token2wav/campplus.onnx
ONNX
models/Step-Audio-2-mini-fork/token2wav/flow.pt
models/Step-Audio-2-mini-fork/token2wav/flow.yaml
models/Step-Audio-2-mini-fork/token2wav/hift.pt
models/Step-Audio-2-mini-fork/token2wav/speech_tokenizer_v2_25hz.onnx
ONNX
models/Step-Audio-2-mini-fork/tokenizer.json
models/Step-Audio-2-mini-fork/tokenizer_config.json
models/Step-Audio-2-mini-fork/vocab.json
models/Step-Audio-2-mini/.gitattributes
models/Step-Audio-2-mini/README.md
models/Step-Audio-2-mini/added_tokens.json
models/Step-Audio-2-mini/assets/architecture5.png
models/Step-Audio-2-mini/assets/arxiv.svg
models/Step-Audio-2-mini/assets/logo.png
models/Step-Audio-2-mini/assets/qrcode.jpg
models/Step-Audio-2-mini/assets/radar.png
models/Step-Audio-2-mini/assets/wechat_group.png
models/Step-Audio-2-mini/config.json
models/Step-Audio-2-mini/configuration_step_audio_2.py
models/Step-Audio-2-mini/merges.txt
models/Step-Audio-2-mini/model-00001-of-00004.safetensors
models/Step-Audio-2-mini/model-00002-of-00004.safetensors
models/Step-Audio-2-mini/model-00003-of-00004.safetensors
models/Step-Audio-2-mini/model-00004-of-00004.safetensors
models/Step-Audio-2-mini/model.safetensors.index.json
models/Step-Audio-2-mini/modeling_step_audio_2.py
models/Step-Audio-2-mini/source.txt
models/Step-Audio-2-mini/special_tokens_map.json
models/Step-Audio-2-mini/token2wav/campplus.onnx
ONNX
models/Step-Audio-2-mini/token2wav/flow.pt
models/Step-Audio-2-mini/token2wav/flow.yaml
models/Step-Audio-2-mini/token2wav/hift.pt
models/Step-Audio-2-mini/token2wav/speech_tokenizer_v2_25hz.onnx
ONNX
models/Step-Audio-2-mini/tokenizer.json
models/Step-Audio-2-mini/tokenizer_config.json
models/Step-Audio-2-mini/vocab.json
models/Step-Audio-AQAA/.gitattributes
models/Step-Audio-AQAA/README.md
models/Step-Audio-AQAA/config.json
models/Step-Audio-AQAA/model-00001.safetensors
models/Step-Audio-AQAA/model-00002.safetensors
models/Step-Audio-AQAA/model-00003.safetensors
models/Step-Audio-AQAA/model-00004.safetensors
models/Step-Audio-AQAA/model-00005.safetensors
models/Step-Audio-AQAA/model-00006.safetensors
models/Step-Audio-AQAA/model-00007.safetensors
models/Step-Audio-AQAA/model-00008.safetensors
models/Step-Audio-AQAA/model-00009.safetensors
models/Step-Audio-AQAA/model-00010.safetensors
models/Step-Audio-AQAA/model-00011.safetensors
models/Step-Audio-AQAA/model-00012.safetensors
models/Step-Audio-AQAA/model-00013.safetensors
models/Step-Audio-AQAA/model-00014.safetensors
models/Step-Audio-AQAA/model-00015.safetensors
models/Step-Audio-AQAA/model-00016.safetensors
models/Step-Audio-AQAA/model-00017.safetensors
models/Step-Audio-AQAA/model-00018.safetensors
models/Step-Audio-AQAA/model-00019.safetensors
models/Step-Audio-AQAA/model-00020.safetensors
models/Step-Audio-AQAA/model-00021.safetensors
models/Step-Audio-AQAA/model-00022.safetensors
models/Step-Audio-AQAA/model-00023.safetensors
models/Step-Audio-AQAA/model-00024.safetensors
models/Step-Audio-AQAA/model-00025.safetensors
models/Step-Audio-AQAA/model-00026.safetensors
models/Step-Audio-AQAA/model-00027.safetensors
models/Step-Audio-AQAA/model-00028.safetensors
models/Step-Audio-AQAA/model.safetensors.index.json
models/Step-Audio-AQAA/preprocessor_config.json
models/Step-Audio-AQAA/source.txt
models/Step-Audio-AQAA/step2_tokenizer_241028.model
models/Step-Audio-Chat/.gitattributes
models/Step-Audio-Chat/README.md
models/Step-Audio-Chat/config.json
models/Step-Audio-Chat/configuration_step1.py
models/Step-Audio-Chat/lib/liboptimus_ths-torch2.2-cu121.cpython-310-x86_64-linux-gnu.so
models/Step-Audio-Chat/lib/liboptimus_ths-torch2.3-cu121.cpython-310-x86_64-linux-gnu.so
models/Step-Audio-Chat/lib/liboptimus_ths-torch2.5-cu124.cpython-310-x86_64-linux-gnu.so
models/Step-Audio-Chat/model-00001.safetensors
models/Step-Audio-Chat/model-00002.safetensors
models/Step-Audio-Chat/model-00003.safetensors
models/Step-Audio-Chat/model-00004.safetensors
models/Step-Audio-Chat/model-00005.safetensors
models/Step-Audio-Chat/model-00006.safetensors
models/Step-Audio-Chat/model-00007.safetensors
models/Step-Audio-Chat/model-00008.safetensors
models/Step-Audio-Chat/model-00009.safetensors
models/Step-Audio-Chat/model-00010.safetensors
models/Step-Audio-Chat/model-00011.safetensors
models/Step-Audio-Chat/model-00012.safetensors
models/Step-Audio-Chat/model-00013.safetensors
models/Step-Audio-Chat/model-00014.safetensors
models/Step-Audio-Chat/model-00015.safetensors
models/Step-Audio-Chat/model-00016.safetensors
models/Step-Audio-Chat/model-00017.safetensors
models/Step-Audio-Chat/model-00018.safetensors
models/Step-Audio-Chat/model-00019.safetensors
models/Step-Audio-Chat/model-00020.safetensors
models/Step-Audio-Chat/model-00021.safetensors
models/Step-Audio-Chat/model-00022.safetensors
models/Step-Audio-Chat/model-00023.safetensors
models/Step-Audio-Chat/model-00024.safetensors
models/Step-Audio-Chat/model-00025.safetensors
models/Step-Audio-Chat/model-00026.safetensors
models/Step-Audio-Chat/model-00027.safetensors
models/Step-Audio-Chat/model.safetensors.index.json
models/Step-Audio-Chat/modeling_step1.py
models/Step-Audio-Chat/source.txt
models/Step-Audio-Chat/tokenizer.model
models/Step-Audio-Chat/tokenizer_config.json
models/Step-Audio-EditX-bnb-4bit/.gitattributes
models/Step-Audio-EditX-bnb-4bit/CosyVoice-300M-25Hz/FLOW_VERSION
models/Step-Audio-EditX-bnb-4bit/CosyVoice-300M-25Hz/campplus.onnx
ONNX
models/Step-Audio-EditX-bnb-4bit/CosyVoice-300M-25Hz/cosyvoice.yaml
models/Step-Audio-EditX-bnb-4bit/CosyVoice-300M-25Hz/flow.pt
models/Step-Audio-EditX-bnb-4bit/CosyVoice-300M-25Hz/hift.pt
models/Step-Audio-EditX-bnb-4bit/CosyVoice-300M-25Hz/speech_tokenizer_v1.onnx
ONNX
models/Step-Audio-EditX-bnb-4bit/README.md
models/Step-Audio-EditX-bnb-4bit/config.json
models/Step-Audio-EditX-bnb-4bit/configuration_step1.py
models/Step-Audio-EditX-bnb-4bit/generation_config.json
models/Step-Audio-EditX-bnb-4bit/model.safetensors
models/Step-Audio-EditX-bnb-4bit/modeling_step1.py
models/Step-Audio-EditX-bnb-4bit/quantization_config.json
models/Step-Audio-EditX-bnb-4bit/source.txt
models/Step-Audio-EditX-bnb-4bit/special_tokens_map.json
models/Step-Audio-EditX-bnb-4bit/tokenizer.json
models/Step-Audio-EditX-bnb-4bit/tokenizer.model
models/Step-Audio-EditX-bnb-4bit/tokenizer_config.json
models/Step-Audio-EditX/.gitattributes
models/Step-Audio-EditX/CosyVoice-300M-25Hz/FLOW_VERSION
models/Step-Audio-EditX/CosyVoice-300M-25Hz/campplus.onnx
ONNX
models/Step-Audio-EditX/CosyVoice-300M-25Hz/cosyvoice.yaml
models/Step-Audio-EditX/CosyVoice-300M-25Hz/flow.pt
models/Step-Audio-EditX/CosyVoice-300M-25Hz/hift.pt
models/Step-Audio-EditX/CosyVoice-300M-25Hz/speech_tokenizer_v1.onnx
ONNX
models/Step-Audio-EditX/README.md
models/Step-Audio-EditX/config.json
models/Step-Audio-EditX/configuration_step1.py
models/Step-Audio-EditX/model-00001.safetensors
models/Step-Audio-EditX/model.safetensors.index.json
models/Step-Audio-EditX/modeling_step1.py
models/Step-Audio-EditX/source.txt
models/Step-Audio-EditX/tokenizer.model
models/Step-Audio-EditX/tokenizer_config.json
models/Step-Audio-R1-NVFP4A16/.gitattributes
models/Step-Audio-R1-NVFP4A16/README.md
models/Step-Audio-R1-NVFP4A16/added_tokens.json
models/Step-Audio-R1-NVFP4A16/chat_template.jinja
models/Step-Audio-R1-NVFP4A16/config.json
models/Step-Audio-R1-NVFP4A16/configuration_step_audio_2.py
models/Step-Audio-R1-NVFP4A16/generation_config.json
models/Step-Audio-R1-NVFP4A16/merges.txt
models/Step-Audio-R1-NVFP4A16/model-00001-of-00005.safetensors
models/Step-Audio-R1-NVFP4A16/model-00002-of-00005.safetensors
models/Step-Audio-R1-NVFP4A16/model-00003-of-00005.safetensors
models/Step-Audio-R1-NVFP4A16/model-00004-of-00005.safetensors
models/Step-Audio-R1-NVFP4A16/model-00005-of-00005.safetensors
models/Step-Audio-R1-NVFP4A16/model.safetensors.index.json
models/Step-Audio-R1-NVFP4A16/modeling_step_audio_2.py
models/Step-Audio-R1-NVFP4A16/recipe.yaml
models/Step-Audio-R1-NVFP4A16/source.txt
models/Step-Audio-R1-NVFP4A16/special_tokens_map.json
models/Step-Audio-R1-NVFP4A16/tokenizer.json
models/Step-Audio-R1-NVFP4A16/tokenizer_config.json
models/Step-Audio-R1-NVFP4A16/vocab.json
models/Step-Audio-TTS-3B/.gitattributes
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz-Music/VERSION_Vq0206Vocoder_Sing_0106
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz-Music/campplus.onnx
ONNX
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz-Music/cosyvoice.yaml
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz-Music/flow.pt
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz-Music/hift.pt
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz-Music/speech_tokenizer_v1.onnx
ONNX
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz/VERSION_Vq0206Vocoder_1202
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz/campplus.onnx
ONNX
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz/cosyvoice.yaml
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz/flow.pt
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz/hift.pt
models/Step-Audio-TTS-3B/CosyVoice-300M-25Hz/speech_tokenizer_v1.onnx
ONNX
models/Step-Audio-TTS-3B/README.md
models/Step-Audio-TTS-3B/config.json
models/Step-Audio-TTS-3B/configuration_step1.py
models/Step-Audio-TTS-3B/lib/liboptimus_ths-torch2.2-cu121.cpython-310-x86_64-linux-gnu.so
models/Step-Audio-TTS-3B/lib/liboptimus_ths-torch2.3-cu121.cpython-310-x86_64-linux-gnu.so
models/Step-Audio-TTS-3B/lib/liboptimus_ths-torch2.5-cu124.cpython-310-x86_64-linux-gnu.so
models/Step-Audio-TTS-3B/model-00001.safetensors
models/Step-Audio-TTS-3B/model.safetensors.index.json
models/Step-Audio-TTS-3B/modeling_step1.py
models/Step-Audio-TTS-3B/source.txt
models/Step-Audio-TTS-3B/tokenizer.model
models/Step-Audio-TTS-3B/tokenizer_config.json
models/Step-Audio-Tokenizer/.gitattributes
models/Step-Audio-Tokenizer/README.md
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/.mdl
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/.msc
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/.mv
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/README.md
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/am.mvn
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/config.yaml
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/configuration.json
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/example/asr_example.wav
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/example/asr_example_普通话.wav
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/example/asr_example_粤语.wav
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/model.pt
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/seg_dict
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/tokens.json
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/tokens.txt
models/Step-Audio-Tokenizer/dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/write_tokens_from_txt.py
models/Step-Audio-Tokenizer/linguistic_tokenizer.npy
models/Step-Audio-Tokenizer/source.txt
models/Step-Audio-Tokenizer/speech_tokenizer_v1.onnx
ONNX
models/StepAudio2mini_BPFT/.gitattributes
models/StepAudio2mini_BPFT/README.md
models/StepAudio2mini_BPFT/adapter_config.json
models/StepAudio2mini_BPFT/adapter_model.safetensors
models/StepAudio2mini_BPFT/added_tokens.json
models/StepAudio2mini_BPFT/checkpoint-12000/README.md
models/StepAudio2mini_BPFT/checkpoint-12000/adapter_config.json
models/StepAudio2mini_BPFT/checkpoint-12000/adapter_model.safetensors
models/StepAudio2mini_BPFT/checkpoint-12000/added_tokens.json
models/StepAudio2mini_BPFT/checkpoint-12000/merges.txt
models/StepAudio2mini_BPFT/checkpoint-12000/special_tokens_map.json
models/StepAudio2mini_BPFT/checkpoint-12000/tokenizer.json
models/StepAudio2mini_BPFT/checkpoint-12000/tokenizer_config.json
models/StepAudio2mini_BPFT/checkpoint-12000/training_args.bin
models/StepAudio2mini_BPFT/checkpoint-12000/vocab.json
models/StepAudio2mini_BPFT/checkpoint-15000/README.md
models/StepAudio2mini_BPFT/checkpoint-15000/adapter_config.json
models/StepAudio2mini_BPFT/checkpoint-15000/adapter_model.safetensors
models/StepAudio2mini_BPFT/checkpoint-15000/added_tokens.json
models/StepAudio2mini_BPFT/checkpoint-15000/merges.txt
models/StepAudio2mini_BPFT/checkpoint-15000/special_tokens_map.json
models/StepAudio2mini_BPFT/checkpoint-15000/tokenizer.json
models/StepAudio2mini_BPFT/checkpoint-15000/tokenizer_config.json
models/StepAudio2mini_BPFT/checkpoint-15000/training_args.bin
models/StepAudio2mini_BPFT/checkpoint-15000/vocab.json
models/StepAudio2mini_BPFT/checkpoint-18000/README.md
models/StepAudio2mini_BPFT/checkpoint-18000/adapter_config.json
models/StepAudio2mini_BPFT/checkpoint-18000/adapter_model.safetensors
models/StepAudio2mini_BPFT/checkpoint-18000/added_tokens.json
models/StepAudio2mini_BPFT/checkpoint-18000/merges.txt
models/StepAudio2mini_BPFT/checkpoint-18000/special_tokens_map.json
models/StepAudio2mini_BPFT/checkpoint-18000/tokenizer.json
models/StepAudio2mini_BPFT/checkpoint-18000/tokenizer_config.json
models/StepAudio2mini_BPFT/checkpoint-18000/training_args.bin
models/StepAudio2mini_BPFT/checkpoint-18000/vocab.json
models/StepAudio2mini_BPFT/checkpoint-18850/README.md
models/StepAudio2mini_BPFT/checkpoint-18850/adapter_config.json
models/StepAudio2mini_BPFT/checkpoint-18850/adapter_model.safetensors
models/StepAudio2mini_BPFT/checkpoint-18850/added_tokens.json
models/StepAudio2mini_BPFT/checkpoint-18850/merges.txt
models/StepAudio2mini_BPFT/checkpoint-18850/special_tokens_map.json
models/StepAudio2mini_BPFT/checkpoint-18850/tokenizer.json
models/StepAudio2mini_BPFT/checkpoint-18850/tokenizer_config.json
models/StepAudio2mini_BPFT/checkpoint-18850/training_args.bin
models/StepAudio2mini_BPFT/checkpoint-18850/vocab.json
models/StepAudio2mini_BPFT/checkpoint-3000/README.md
models/StepAudio2mini_BPFT/checkpoint-3000/adapter_config.json
models/StepAudio2mini_BPFT/checkpoint-3000/adapter_model.safetensors
models/StepAudio2mini_BPFT/checkpoint-3000/added_tokens.json
models/StepAudio2mini_BPFT/checkpoint-3000/merges.txt
models/StepAudio2mini_BPFT/checkpoint-3000/special_tokens_map.json
models/StepAudio2mini_BPFT/checkpoint-3000/tokenizer.json
models/StepAudio2mini_BPFT/checkpoint-3000/tokenizer_config.json
models/StepAudio2mini_BPFT/checkpoint-3000/training_args.bin
models/StepAudio2mini_BPFT/checkpoint-3000/vocab.json
models/StepAudio2mini_BPFT/checkpoint-6000/README.md
models/StepAudio2mini_BPFT/checkpoint-6000/adapter_config.json
models/StepAudio2mini_BPFT/checkpoint-6000/adapter_model.safetensors
models/StepAudio2mini_BPFT/checkpoint-6000/added_tokens.json
models/StepAudio2mini_BPFT/checkpoint-6000/merges.txt
models/StepAudio2mini_BPFT/checkpoint-6000/special_tokens_map.json
models/StepAudio2mini_BPFT/checkpoint-6000/tokenizer.json
models/StepAudio2mini_BPFT/checkpoint-6000/tokenizer_config.json
models/StepAudio2mini_BPFT/checkpoint-6000/training_args.bin
models/StepAudio2mini_BPFT/checkpoint-6000/vocab.json
models/StepAudio2mini_BPFT/checkpoint-9000/README.md
models/StepAudio2mini_BPFT/checkpoint-9000/adapter_config.json
models/StepAudio2mini_BPFT/checkpoint-9000/adapter_model.safetensors
models/StepAudio2mini_BPFT/checkpoint-9000/added_tokens.json
models/StepAudio2mini_BPFT/checkpoint-9000/merges.txt
models/StepAudio2mini_BPFT/checkpoint-9000/special_tokens_map.json
models/StepAudio2mini_BPFT/checkpoint-9000/tokenizer.json
models/StepAudio2mini_BPFT/checkpoint-9000/tokenizer_config.json
models/StepAudio2mini_BPFT/checkpoint-9000/training_args.bin
models/StepAudio2mini_BPFT/checkpoint-9000/vocab.json
models/StepAudio2mini_BPFT/merges.txt
models/StepAudio2mini_BPFT/source.txt
models/StepAudio2mini_BPFT/special_tokens_map.json
models/StepAudio2mini_BPFT/tokenizer.json
models/StepAudio2mini_BPFT/tokenizer_config.json
models/StepAudio2mini_BPFT/vocab.json
tools/StepEval-Audio-Toolcall/.gitattributes
tools/StepEval-Audio-Toolcall/LLM_judge.py
tools/StepEval-Audio-Toolcall/README.md
tools/StepEval-Audio-Toolcall/get_date_time_negative.jsonl
tools/StepEval-Audio-Toolcall/get_date_time_positive.jsonl
tools/StepEval-Audio-Toolcall/get_weather_negative.jsonl
tools/StepEval-Audio-Toolcall/get_weather_positive.jsonl
tools/StepEval-Audio-Toolcall/source.txt
tools/StepEval-Audio-Toolcall/timbre_negative.jsonl
tools/StepEval-Audio-Toolcall/timbre_positive.jsonl
tools/StepEval-Audio-Toolcall/wav.tar
tools/StepEval-Audio-Toolcall/web_search_negative.jsonl
tools/StepEval-Audio-Toolcall/web_search_positive.jsonl
Related models
More from niobures
More models
No task type declared.