lfeats 0.2.1__tar.gz → 0.2.3__tar.gz

{lfeats-0.2.1 → lfeats-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: lfeats
-Version: 0.2.1
+Version: 0.2.3
 Summary: A unified interface to extract hidden representations from speech foundation models
 Project-URL: Documentation, https://takenori-y.github.io/lfeats/stable/
 Project-URL: Source, https://github.com/takenori-y/lfeats
@@ -33,6 +33,7 @@ Requires-Dist: soundfile>=0.10.2
 Requires-Dist: soxr>=0.4.0
 Requires-Dist: torch>=2.6.0
 Requires-Dist: torchaudio>=2.6.0
+Requires-Dist: tqdm>=4.63.0
 Requires-Dist: transformers>=5.3.0
 Provides-Extra: dev
 Requires-Dist: build; extra == 'dev'
@@ -41,7 +42,7 @@ Requires-Dist: mdformat; extra == 'dev'
 Requires-Dist: numpydoc; extra == 'dev'
 Requires-Dist: pkginfo; extra == 'dev'
 Requires-Dist: pydata-sphinx-theme; extra == 'dev'
-Requires-Dist: pyright<=1.1.408; extra == 'dev'
+Requires-Dist: pyright[nodejs]; extra == 'dev'
 Requires-Dist: pytest; extra == 'dev'
 Requires-Dist: pytest-cov; extra == 'dev'
 Requires-Dist: ruff; extra == 'dev'
@@ -129,6 +130,7 @@ pip install git+https://github.com/takenori-y/lfeats.git@master
 | `unispeech-sat` | `base` | 12 | 768 | [arXiv](https://arxiv.org/abs/2110.05752) | [GitHub](https://github.com/microsoft/UniSpeech) | [🤗](https://huggingface.co/microsoft/unispeech-sat-base) |
 | | `base+` | 12 | 768 | | | [🤗](https://huggingface.co/microsoft/unispeech-sat-base-plus) |
 | | `large` | 24 | 1024 | | | [🤗](https://huggingface.co/microsoft/unispeech-sat-large) |
+| `w2v-bert2` | `base` | 24 | 1024 | [arXiv](https://arxiv.org/abs/2312.05187) | [GitHub](https://github.com/facebookresearch/seamless_communication) | [🤗](https://huggingface.co/facebook/w2v-bert-2.0) |
 | `wav2vec2` | `base` | 12 | 768 | [arXiv](https://arxiv.org/abs/2006.11477) | [GitHub](https://github.com/facebookresearch/fairseq/tree/main/examples/wav2vec) | |
 | | `large` | 24 | 1024 | | | |
 | | `xlsr` | 24 | 1024 | [arXiv](https://arxiv.org/abs/2006.13979) | | |
@@ -148,25 +150,38 @@ pip install git+https://github.com/takenori-y/lfeats.git@master
 
 | Model Name | Model Variant | Hop Size [ms] | Dimension | Paper | Source | Model Hub |
 | :--- | :--- | ---: | ---: | :---: | :---: | :---: |
-| `higgs-audio` | `v2` | 40 | 1024 | | [GitHub](https://github.com/boson-ai/higgs-audio) | [🤗](https://huggingface.co/eustlb/higgs-audio-v2-tokenizer) |
+| `dacvae` | `base` | 40 | 128 | [arXiv](https://arxiv.org/abs/2410.13720) | [GitHub](https://github.com/facebookresearch/dacvae) | [🤗](https://huggingface.co/facebook/dacvae-watermarked) |
+| `higgs-audio` | `v2` | 40 | 1024 | [Blog](https://github.com/Render-AI-Code/cog-higgs-audio/blob/main/tech_blogs/TOKENIZER_BLOG.md) | [GitHub](https://github.com/boson-ai/higgs-audio) | [🤗](https://huggingface.co/eustlb/higgs-audio-v2-tokenizer) |
+| `mimi` | `base` | 80 | 512 | [arXiv](https://arxiv.org/abs/2410.00037) | [GitHub](https://github.com/kyutai-labs/moshi) | [🤗](https://huggingface.co/kyutai/mimi) |
+| `x-codec` | `hubert` | 20 | 1024 | [arXiv](https://arxiv.org/abs/2408.17175) | [GitHub](https://github.com/zhenye234/xcodec) | [🤗](https://huggingface.co/hf-audio/xcodec-hubert-librispeech) |
+| | `wavlm` | 20 | 1024 | | | [🤗](https://huggingface.co/hf-audio/xcodec-wavlm-more-data) |
 
 ### Utterance-Level Features
 
-| Model Name | Model Variant | Layers | Dimension | Paper | Source | Model Hub |
-| :--- | :--- | ---: | ---: | :---: | :---: | :---: |
-| `ecapa-tdnn` | `base` | 0 | 192 | [arXiv](https://arxiv.org/abs/2005.07143) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb) |
-| `next-tdnn` | `light` | 0 | 192 | [arXiv](https://arxiv.org/abs/2312.08603) | [GitHub](https://github.com/dmlguq456/NeXt_TDNN_ASV) | |
-| | `base` | 0 | 192 | | | |
-| | `base-v2` | 0 | 192 | | | |
-| `r-vector` | `base` | 0 | 256 | [arXiv](https://arxiv.org/abs/1910.12592) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-resnet-voxceleb) |
-| `redimnet` | `b0` | 0 | 192 | [arXiv](https://arxiv.org/abs/2407.18223) | [GitHub](https://github.com/IDRnD/redimnet) | |
-| | `b1` | 0 | 192 | | | |
-| | `b2` | 0 | 192 | | | |
-| | `b3` | 0 | 192 | | | |
-| | `b4` | 0 | 192 | | | |
-| | `b5` | 0 | 192 | | | |
-| | `b6` | 0 | 192 | | | |
-| `x-vector` | `base` | 0 | 512 | [IEEE](https://ieeexplore.ieee.org/document/8461375) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-xvect-voxceleb) |
+| Model Name | Model Variant | Dimension | Paper | Source | Model Hub |
+| :--- | :--- | ---: | :---: | :---: | :---: |
+| `ecapa-tdnn` | `base` | 192 | [arXiv](https://arxiv.org/abs/2005.07143) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb) |
+| `next-tdnn` | `light` | 192 | [arXiv](https://arxiv.org/abs/2312.08603) | [GitHub](https://github.com/dmlguq456/NeXt_TDNN_ASV) | |
+| | `base` | 192 | | | |
+| | `base-v2` | 192 | | | |
+| `r-vector` | `base` | 256 | [arXiv](https://arxiv.org/abs/1910.12592) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-resnet-voxceleb) |
+| `redimnet` | `b0` | 192 | [arXiv](https://arxiv.org/abs/2407.18223) | [GitHub](https://github.com/IDRnD/redimnet) | |
+| | `b1` | 192 | | | |
+| | `b2` | 192 | | | |
+| | `b3` | 192 | | | |
+| | `b4` | 192 | | | |
+| | `b5` | 192 | | | |
+| | `b6` | 192 | | | |
+| `redimnet2` | `b0` | 192 | [arXiv](https://arxiv.org/abs/2603.11841) | [GitHub](https://github.com/PalabraAI/redimnet2) | |
+| | `b1` | 192 | | | |
+| | `b2` | 192 | | | |
+| | `b3` | 192 | | | |
+| | `b4` | 192 | | | |
+| | `b5` | 192 | | | |
+| | `b6` | 192 | | | |
+| `wavlm-sv` | `base` | 512 | [arXiv](https://arxiv.org/abs/2110.13900) | [GitHub](https://github.com/microsoft/unilm/tree/master/wavlm) | [🤗](https://huggingface.co/microsoft/wavlm-base-sv) |
+| | `base+` | 512 | | | [🤗](https://huggingface.co/microsoft/wavlm-base-plus-sv) |
+| `x-vector` | `base` | 512 | [IEEE](https://ieeexplore.ieee.org/document/8461375) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-xvect-voxceleb) |
 
 > [!IMPORTANT]
 > Users must comply with the respective licenses of the models.
@@ -347,10 +362,11 @@ This project is released under the MIT License.
 
 | Repository | License |
 | :--- | :--- |
+| [DAC-VAE](https://github.com/facebookresearch/dacvae) | Apache-2.0 |
 | [fairseq](https://github.com/facebookresearch/fairseq) | MIT |
-| [NeXt_TDNN_ASV](https://github.com/dmlguq456/NeXt_TDNN_ASV) | Apache-2.0 |
+| [NeXt-TDNN](https://github.com/dmlguq456/NeXt_TDNN_ASV) | Apache-2.0 |
 | [R-Spin](https://github.com/vectominist/rspin) | MIT |
 | [S3PRL](https://github.com/s3prl/s3prl) | Apache-2.0 |
 | [SpeechBrain](https://github.com/speechbrain/speechbrain) | Apache-2.0 |
 | [Spin](https://github.com/vectominist/spin) | MIT |
-| [timm](https://github.com/huggingface/pytorch-image-models) | Apache-2.0 |
+| [TIMM](https://github.com/huggingface/pytorch-image-models) | Apache-2.0 |

{lfeats-0.2.1 → lfeats-0.2.3}/README.md

@@ -78,6 +78,7 @@ pip install git+https://github.com/takenori-y/lfeats.git@master
 | `unispeech-sat` | `base` | 12 | 768 | [arXiv](https://arxiv.org/abs/2110.05752) | [GitHub](https://github.com/microsoft/UniSpeech) | [🤗](https://huggingface.co/microsoft/unispeech-sat-base) |
 | | `base+` | 12 | 768 | | | [🤗](https://huggingface.co/microsoft/unispeech-sat-base-plus) |
 | | `large` | 24 | 1024 | | | [🤗](https://huggingface.co/microsoft/unispeech-sat-large) |
+| `w2v-bert2` | `base` | 24 | 1024 | [arXiv](https://arxiv.org/abs/2312.05187) | [GitHub](https://github.com/facebookresearch/seamless_communication) | [🤗](https://huggingface.co/facebook/w2v-bert-2.0) |
 | `wav2vec2` | `base` | 12 | 768 | [arXiv](https://arxiv.org/abs/2006.11477) | [GitHub](https://github.com/facebookresearch/fairseq/tree/main/examples/wav2vec) | |
 | | `large` | 24 | 1024 | | | |
 | | `xlsr` | 24 | 1024 | [arXiv](https://arxiv.org/abs/2006.13979) | | |
@@ -97,25 +98,38 @@ pip install git+https://github.com/takenori-y/lfeats.git@master
 
 | Model Name | Model Variant | Hop Size [ms] | Dimension | Paper | Source | Model Hub |
 | :--- | :--- | ---: | ---: | :---: | :---: | :---: |
-| `higgs-audio` | `v2` | 40 | 1024 | | [GitHub](https://github.com/boson-ai/higgs-audio) | [🤗](https://huggingface.co/eustlb/higgs-audio-v2-tokenizer) |
+| `dacvae` | `base` | 40 | 128 | [arXiv](https://arxiv.org/abs/2410.13720) | [GitHub](https://github.com/facebookresearch/dacvae) | [🤗](https://huggingface.co/facebook/dacvae-watermarked) |
+| `higgs-audio` | `v2` | 40 | 1024 | [Blog](https://github.com/Render-AI-Code/cog-higgs-audio/blob/main/tech_blogs/TOKENIZER_BLOG.md) | [GitHub](https://github.com/boson-ai/higgs-audio) | [🤗](https://huggingface.co/eustlb/higgs-audio-v2-tokenizer) |
+| `mimi` | `base` | 80 | 512 | [arXiv](https://arxiv.org/abs/2410.00037) | [GitHub](https://github.com/kyutai-labs/moshi) | [🤗](https://huggingface.co/kyutai/mimi) |
+| `x-codec` | `hubert` | 20 | 1024 | [arXiv](https://arxiv.org/abs/2408.17175) | [GitHub](https://github.com/zhenye234/xcodec) | [🤗](https://huggingface.co/hf-audio/xcodec-hubert-librispeech) |
+| | `wavlm` | 20 | 1024 | | | [🤗](https://huggingface.co/hf-audio/xcodec-wavlm-more-data) |
 
 ### Utterance-Level Features
 
-| Model Name | Model Variant | Layers | Dimension | Paper | Source | Model Hub |
-| :--- | :--- | ---: | ---: | :---: | :---: | :---: |
-| `ecapa-tdnn` | `base` | 0 | 192 | [arXiv](https://arxiv.org/abs/2005.07143) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb) |
-| `next-tdnn` | `light` | 0 | 192 | [arXiv](https://arxiv.org/abs/2312.08603) | [GitHub](https://github.com/dmlguq456/NeXt_TDNN_ASV) | |
-| | `base` | 0 | 192 | | | |
-| | `base-v2` | 0 | 192 | | | |
-| `r-vector` | `base` | 0 | 256 | [arXiv](https://arxiv.org/abs/1910.12592) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-resnet-voxceleb) |
-| `redimnet` | `b0` | 0 | 192 | [arXiv](https://arxiv.org/abs/2407.18223) | [GitHub](https://github.com/IDRnD/redimnet) | |
-| | `b1` | 0 | 192 | | | |
-| | `b2` | 0 | 192 | | | |
-| | `b3` | 0 | 192 | | | |
-| | `b4` | 0 | 192 | | | |
-| | `b5` | 0 | 192 | | | |
-| | `b6` | 0 | 192 | | | |
-| `x-vector` | `base` | 0 | 512 | [IEEE](https://ieeexplore.ieee.org/document/8461375) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-xvect-voxceleb) |
+| Model Name | Model Variant | Dimension | Paper | Source | Model Hub |
+| :--- | :--- | ---: | :---: | :---: | :---: |
+| `ecapa-tdnn` | `base` | 192 | [arXiv](https://arxiv.org/abs/2005.07143) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb) |
+| `next-tdnn` | `light` | 192 | [arXiv](https://arxiv.org/abs/2312.08603) | [GitHub](https://github.com/dmlguq456/NeXt_TDNN_ASV) | |
+| | `base` | 192 | | | |
+| | `base-v2` | 192 | | | |
+| `r-vector` | `base` | 256 | [arXiv](https://arxiv.org/abs/1910.12592) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-resnet-voxceleb) |
+| `redimnet` | `b0` | 192 | [arXiv](https://arxiv.org/abs/2407.18223) | [GitHub](https://github.com/IDRnD/redimnet) | |
+| | `b1` | 192 | | | |
+| | `b2` | 192 | | | |
+| | `b3` | 192 | | | |
+| | `b4` | 192 | | | |
+| | `b5` | 192 | | | |
+| | `b6` | 192 | | | |
+| `redimnet2` | `b0` | 192 | [arXiv](https://arxiv.org/abs/2603.11841) | [GitHub](https://github.com/PalabraAI/redimnet2) | |
+| | `b1` | 192 | | | |
+| | `b2` | 192 | | | |
+| | `b3` | 192 | | | |
+| | `b4` | 192 | | | |
+| | `b5` | 192 | | | |
+| | `b6` | 192 | | | |
+| `wavlm-sv` | `base` | 512 | [arXiv](https://arxiv.org/abs/2110.13900) | [GitHub](https://github.com/microsoft/unilm/tree/master/wavlm) | [🤗](https://huggingface.co/microsoft/wavlm-base-sv) |
+| | `base+` | 512 | | | [🤗](https://huggingface.co/microsoft/wavlm-base-plus-sv) |
+| `x-vector` | `base` | 512 | [IEEE](https://ieeexplore.ieee.org/document/8461375) | [GitHub](https://github.com/speechbrain/speechbrain) | [🤗](https://huggingface.co/speechbrain/spkrec-xvect-voxceleb) |
 
 > [!IMPORTANT]
 > Users must comply with the respective licenses of the models.
@@ -296,10 +310,11 @@ This project is released under the MIT License.
 
 | Repository | License |
 | :--- | :--- |
+| [DAC-VAE](https://github.com/facebookresearch/dacvae) | Apache-2.0 |
 | [fairseq](https://github.com/facebookresearch/fairseq) | MIT |
-| [NeXt_TDNN_ASV](https://github.com/dmlguq456/NeXt_TDNN_ASV) | Apache-2.0 |
+| [NeXt-TDNN](https://github.com/dmlguq456/NeXt_TDNN_ASV) | Apache-2.0 |
 | [R-Spin](https://github.com/vectominist/rspin) | MIT |
 | [S3PRL](https://github.com/s3prl/s3prl) | Apache-2.0 |
 | [SpeechBrain](https://github.com/speechbrain/speechbrain) | Apache-2.0 |
 | [Spin](https://github.com/vectominist/spin) | MIT |
-| [timm](https://github.com/huggingface/pytorch-image-models) | Apache-2.0 |
+| [TIMM](https://github.com/huggingface/pytorch-image-models) | Apache-2.0 |

{lfeats-0.2.1 → lfeats-0.2.3}/lfeats/cli.py

@@ -12,6 +12,8 @@ import os
 import sys
 from pathlib import Path
 
+from tqdm import tqdm
+
 logger = logging.getLogger("lfeats")
 
 
@@ -120,11 +122,18 @@ def get_arguments() -> argparse.Namespace:
         "--reduction",
         type=str,
         default="auto",
+        choices=["none", "mean", "auto"],
         help=(
             "The reduction method to apply to the extracted features. Can be 'none', "
             "'mean', or 'auto'."
         ),
     )
+    parser.add_argument(
+        "--normalize",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Enable or disable L2 normalization of the extracted features.",
+    )
     parser.add_argument(
         "-q",
         "--quiet",
@@ -163,6 +172,7 @@ def main() -> None:
         for root, _, files in os.walk(args.source):
             for file in files:
                 input_files.append(os.path.join(root, file))
+        input_files = sorted(input_files)
     else:
         raise ValueError(f"Invalid source: {args.source}")
 
@@ -174,12 +184,14 @@ def main() -> None:
     # Parse the layers argument.
     if args.layers in ("all", "last"):
         layers = args.layers
-    elif "," in args.layers:
-        layers = [int(layer.strip()) for layer in args.layers.split(",")]
-    elif args.layers.isdigit():
-        layers = int(args.layers)
     else:
-        raise ValueError(f"Invalid layers argument: {args.layers}")
+        try:
+            if "," in args.layers:
+                layers = [int(layer.strip()) for layer in args.layers.split(",")]
+            else:
+                layers = int(args.layers)
+        except ValueError as e:
+            raise ValueError(f"Invalid layers argument: {args.layers}") from e
 
     output_ext = {
         "npz": "npz",
@@ -197,12 +209,15 @@ def main() -> None:
         device=args.device,
         cache_dir=args.cache_dir,
     )
+    logger.info(f"Loading {extractor.get_model_id()} model...")
     extractor.load(quiet=args.quiet)
 
     num_errors = 0
 
     # Process each input file and extract features.
-    for input_file in input_files:
+    for input_file in tqdm(
+        input_files, desc="Processing files", unit="file", disable=args.quiet
+    ):
         if not os.path.isfile(input_file):
             logger.error(f"Could not find file: {input_file}. Skipping.")
             num_errors += 1
@@ -244,6 +259,7 @@ def main() -> None:
                 overlap_length_sec=args.overlap_length_sec,
                 upsample_factor=args.upsample_factor,
                 reduction=args.reduction,
+                normalize=args.normalize,
             )
         except Exception as e:
             logger.error(f"Error processing file {input_file}: {e}. Skipping.")

{lfeats-0.2.1 → lfeats-0.2.3}/lfeats/interfaces/extractor.py

@@ -102,6 +102,17 @@ class Extractor:
         self.model_manager.to(device)
         self.resampler_manager.to(device)
 
+    def get_model_id(self) -> str:
+        """Return the identifier of the model being used.
+
+        Returns
+        -------
+        out : str
+            The identifier of the model being used.
+
+        """
+        return self.model_manager.get_model().model_id
+
     def __call__(
         self,
         source: np.ndarray | torch.Tensor | Audio,
@@ -113,6 +124,7 @@ class Extractor:
         overlap_length_sec: int = 5,
         upsample_factor: int = 1,
         reduction: Literal["none", "mean", "auto"] = "auto",
+        normalize: bool = False,
     ) -> Features:
         """Extract features from the input waveform.
 
@@ -148,6 +160,9 @@ class Extractor:
             determined based on the feature granularity ('none' for frame-level features
             and 'mean' for utterance-level features).
 
+        normalize : bool, optional
+            If True, the extracted features will be L2-normalized.
+
         Returns
         -------
         out : Features
@@ -188,14 +203,17 @@ class Extractor:
                 chunk_length_sec=chunk_length_sec,
                 overlap_length_sec=overlap_length_sec,
                 reduction=reduction,
+                normalize=normalize,
             )
 
         model = self.model_manager.get_model()
         if model.granularity != Granularity.FRAME or reduction == "mean":
             raise ValueError("Upsampling is only supported for frame-level features.")
 
-        # Prepare the audio data and validate the upsample factor.
+        # Prepare the audio data at the model's sample rate so that the shifts below
+        # are measured in the same unit as the frame shift.
         audio = create_audio_object(source, sample_rate)
+        audio = self._resample(audio, model.sample_rate)
         B, T = audio.data.shape
         frame_shift = model.frame_shift
         if frame_shift % upsample_factor != 0:
@@ -209,8 +227,10 @@ class Extractor:
         shifted_waveforms = audio.zeros((B * upsample_factor, T))
         for i in range(upsample_factor):
             offset = i * step
-            end = T - offset
-            shifted_waveforms[i::upsample_factor, :end] = audio.data[:, offset:]  # type: ignore
+            if offset < T:
+                shifted_waveforms[i::upsample_factor, : T - offset] = audio.data[  # type: ignore
+                    :, offset:
+                ]
 
         # Extract features from the shifted waveforms.
         features = self._extract(
@@ -220,6 +240,7 @@ class Extractor:
             center=center,
             chunk_length_sec=chunk_length_sec,
             overlap_length_sec=overlap_length_sec,
+            normalize=normalize,
         )
 
         # Interleave the features from the shifted waveforms.
@@ -243,6 +264,7 @@ class Extractor:
         chunk_length_sec: int = 30,
         overlap_length_sec: int = 5,
         reduction: Literal["none", "mean", "auto"] = "auto",
+        normalize: bool = False,
     ) -> Features:
         """Extract features from the input waveform.
 
@@ -275,6 +297,9 @@ class Extractor:
             determined based on the feature granularity ('none' for frame-level features
             and 'mean' for utterance-level features).
 
+        normalize : bool, optional
+            If True, the extracted features will be L2-normalized.
+
         Returns
         -------
         out : Features
@@ -301,17 +326,16 @@ class Extractor:
         model.load(self.cache_dir, quiet=False)
         if model.chunk_length_sec is not None:
             chunk_length_sec = model.chunk_length_sec
+            if chunk_length_sec <= overlap_length_sec:
+                raise ValueError(
+                    f"overlap_length_sec ({overlap_length_sec}) must be less than the "
+                    f"model's fixed chunk length ({chunk_length_sec})."
+                )
         normalized_layers = self._normalize_layers(layers, model.num_layers + 1)
 
         # Prepare the audio data.
         audio = create_audio_object(source, sample_rate)
-
-        # Resample the audio if needed.
-        if audio.sample_rate != model.sample_rate:
-            resampler = self.resampler_manager.get_resampler(
-                audio.sample_rate, model.sample_rate
-            )
-            audio = resampler.resample(audio)
+        audio = self._resample(audio, model.sample_rate)
         expected_num_frames = self._get_num_frames(audio.length, model.frame_shift)
 
         # Pad the audio if needed.
@@ -377,8 +401,34 @@ class Extractor:
         ):
             features = features.reduce("mean")
 
+        # Apply normalization if specified.
+        if normalize:
+            features = features.normalize()
+
         return features
 
+    def _resample(self, audio: Audio, sample_rate: int) -> Audio:
+        """Resample the audio to the specified sample rate if needed.
+
+        Parameters
+        ----------
+        audio : Audio
+            The input audio data.
+
+        sample_rate : int
+            The target sample rate in Hz.
+
+        Returns
+        -------
+        out : Audio
+            The resampled audio data.
+
+        """
+        if audio.sample_rate == sample_rate:
+            return audio
+        resampler = self.resampler_manager.get_resampler(audio.sample_rate, sample_rate)
+        return resampler.resample(audio)
+
     @staticmethod
     def _get_num_frames(length: int, frame_shift: int) -> int:
         """Calculate the number of frames for a given sample length.

{lfeats-0.2.1 → lfeats-0.2.3}/lfeats/interfaces/types.py

@@ -356,6 +356,26 @@ class Features(Container):
 
         return Features(data=reduced_data, source=self.source, layers=self.layers)
 
+    def normalize(self) -> Features:
+        """Normalize the features in the L2 sense along the feature dimension.
+
+        Returns
+        -------
+        out : Features
+            A new Features instance with normalized data.
+
+        """
+        eps = 1e-12
+        if isinstance(self.data, np.ndarray):
+            norm = np.linalg.norm(self.array, ord=2, axis=-1, keepdims=True)
+            normalized_data = self.array / np.maximum(norm, eps)
+        else:
+            normalized_data = torch.nn.functional.normalize(
+                self.tensor, p=2, dim=-1, eps=eps
+            )
+
+        return Features(data=normalized_data, source=self.source, layers=self.layers)
+
     def concat(self, other: Features) -> Features:
         """Concatenate this Features instance with another one along the time dimension.
 

{lfeats-0.2.1 → lfeats-0.2.3}/lfeats/models/__init__.py

@@ -4,6 +4,7 @@
 """The module for audio feature extraction models."""
 
 from .contentvec import ContentVecModel
+from .dacvae import DACVAEModel
 from .data2vec import Data2VecModel
 from .data2vec2 import Data2Vec2Model
 from .ecapa_tdnn import EcapaTDNNModel
@@ -12,21 +13,27 @@ from .emotion2vec_plus import Emotion2VecPlusModel
 from .higgs_audio import HiggsAudioTokenizerModel
 from .hubert import HuBERTModel
 from .manager import ModelManager
+from .mimi import MimiModel
 from .next_tdnn import NeXtTDNNModel
 from .r_spin import RSpinModel
 from .r_vector import RVectorModel
 from .redimnet import ReDimNetModel
+from .redimnet2 import ReDimNet2Model
 from .spidr import SpidRModel
 from .spin import SpinModel
 from .sslzip import SSLZipModel
 from .unispeech_sat import UniSpeechSATModel
+from .w2v_bert2 import W2VBert2Model
 from .wav2vec2 import Wav2Vec2Model
 from .wavlm import WavLMModel
+from .wavlm_sv import WavLMSVModel
 from .whisper import WhisperModel
+from .x_codec import XCodecModel
 from .x_vector import XVectorModel
 
 MODEL_MAP = {
     "contentvec": ContentVecModel,
+    "dacvae": DACVAEModel,
     "data2vec": Data2VecModel,
     "data2vec2": Data2Vec2Model,
     "ecapa-tdnn": EcapaTDNNModel,
@@ -34,21 +41,26 @@ MODEL_MAP = {
     "emotion2vec+": Emotion2VecPlusModel,
     "higgs-audio": HiggsAudioTokenizerModel,
     "hubert": HuBERTModel,
+    "mimi": MimiModel,
     "next-tdnn": NeXtTDNNModel,
     "r-spin": RSpinModel,
     "r-vector": RVectorModel,
     "redimnet": ReDimNetModel,
+    "redimnet2": ReDimNet2Model,
     "spidr": SpidRModel,
     "spin": SpinModel,
     "sslzip": SSLZipModel,
     "unispeech-sat": UniSpeechSATModel,
+    "w2v-bert2": W2VBert2Model,
     "wav2vec2": Wav2Vec2Model,
     "wavlm": WavLMModel,
+    "wavlm-sv": WavLMSVModel,
     "whisper": WhisperModel,
+    "x-codec": XCodecModel,
     "x-vector": XVectorModel,
 }
 
 __all__ = [
-    "ModelManager",
     "MODEL_MAP",
+    "ModelManager",
 ]

{lfeats-0.2.1 → lfeats-0.2.3}/lfeats/models/base.py

@@ -281,7 +281,7 @@ class TokenLevelFeatureModel(BaseModel):
             The frame shift in samples.
 
         """
-        return int(40.0 * self.sample_rate / 1000)
+        return int(20.0 * self.sample_rate / 1000)
 
     @property
     def center_offset(self) -> int: