avex 0.5.0a1__tar.gz

avex-0.5.0a1/PKG-INFO

@@ -0,0 +1,259 @@
+Metadata-Version: 2.3
+Name: avex
+Version: 0.5.0a1
+Summary: A comprehensive Python-based system for training, evaluating, and analyzing audio representation learning models with support for both supervised and self-supervised learning paradigms
+Keywords: audio,machine-learning,avex,self-supervised,bioacoustics
+Author: Earth Species
+Author-email: Earth Species <contact@earthspecies.org>
+License: MIT
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
+Requires-Dist: librosa>=0.11.0
+Requires-Dist: numpy>=1.26.4
+Requires-Dist: omegaconf>=2.3.0
+Requires-Dist: pydantic>=2.11.3
+Requires-Dist: pyyaml>=6.0.2
+Requires-Dist: soundfile>=0.13.1
+Requires-Dist: birdnetlib>=0.18.0
+Requires-Dist: timm>=1.0.15
+Requires-Dist: torch>=2.5.0
+Requires-Dist: torchaudio>=2.2.0
+Requires-Dist: torchvision>=0.17.0
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: huggingface-hub>=0.36.0
+Requires-Dist: transformers>=4.0.0
+Requires-Dist: h5py>=3.13.0
+Requires-Dist: tensorflow>=2.17.0
+Requires-Dist: tensorflow-hub>=0.16.1
+Requires-Dist: einops>=0.8.1
+Requires-Dist: pydantic-settings>=2.9.1
+Requires-Dist: fsspec>=2024.2.0
+Requires-Dist: gcsfs>=2024.2.0
+Requires-Dist: s3fs>=2024.2.0
+Requires-Dist: pandas>=2.2.3
+Requires-Dist: pytorch-lightning>=2.5.1.post0 ; extra == 'dev'
+Requires-Dist: mlflow>=2.22.0 ; extra == 'dev'
+Requires-Dist: wandb>=0.21.0 ; extra == 'dev'
+Requires-Dist: esp-sweep>=0.1.0 ; extra == 'dev'
+Requires-Dist: esp-data>=1.5.0 ; extra == 'dev'
+Requires-Dist: gradio>=4.0.0 ; extra == 'dev'
+Requires-Dist: gradio-leaderboard>=0.0.13 ; extra == 'dev'
+Requires-Python: >=3.10, <3.13
+Project-URL: Homepage, https://github.com/earthspecies/avex
+Project-URL: Repository, https://github.com/earthspecies/avex
+Project-URL: Documentation, https://github.com/earthspecies/avex#readme
+Project-URL: Bug Tracker, https://github.com/earthspecies/avex/issues
+Provides-Extra: dev
+Description-Content-Type: text/markdown
+
+# avex - Animal Vocalization Encoder Library
+
+![CI status](https://github.com/earthspecies/avex/actions/workflows/pythonapp.yml/badge.svg?branch=main)
+![Pre-commit status](https://github.com/earthspecies/avex/actions/workflows/pre-commit.yml/badge.svg?branch=main)
+
+An API for model loading and inference, and a Python-based system for training and evaluating bioacoustics representation learning models.
+
+## Description
+
+The Animal Vocalization Encoder library avex provides a unified interface for working with pre-trained bioacoustics representation learning models, with support for:
+
+- **Model Loading**: Load pre-trained models with checkpoints and class mappings
+- **Embedding Extraction**: Extract features from audio for downstream tasks
+- **Probe System**: Flexible probe heads (linear, MLP, LSTM, attention, transformer) for transfer learning
+- **Training & Evaluation**: Scripts for supervised learning experiments
+- **Plugin Architecture**: Register and use custom models seamlessly
+
+## Installation
+
+### Prerequisites
+
+- Python 3.10, 3.11, or 3.12
+
+### Install with pip
+
+```bash
+pip install avex
+```
+
+### Install with uv
+
+```bash
+uv add avex
+```
+
+For development installation with training/evaluation tools, see the [Contributing guide](CONTRIBUTING.md).
+
+## Quick Start
+
+```python
+import torch
+import librosa
+from avex import load_model, list_models
+
+# List available models
+print(list_models().keys())
+
+# Load a pre-trained model
+model = load_model("esp_aves2_sl_beats_all", device="cpu")
+
+# Load and preprocess audio (BEATs expects 16kHz)
+audio, sr = librosa.load("your_audio.wav", sr=16000)
+audio_tensor = torch.tensor(audio).unsqueeze(0)  # Shape: (1, num_samples)
+
+# Run inference
+with torch.no_grad():
+    logits = model(audio_tensor)
+    predicted_class = logits.argmax(dim=-1).item()
+
+# Get human-readable label
+if model.label_mapping:
+    label = model.label_mapping.get(str(predicted_class), predicted_class)
+    print(f"Predicted: {label}")
+```
+
+### Embedding Extraction
+
+```python
+# Load for embedding extraction (no classifier head)
+model = load_model("esp_aves2_sl_beats_all", return_features_only=True, device="cpu")
+
+with torch.no_grad():
+    embeddings = model(audio_tensor)
+    # Shape: (batch, time_steps, 768) for BEATs
+
+# Pool to get fixed-size embedding
+embedding = embeddings.mean(dim=1)  # Shape: (batch, 768)
+```
+
+### Transfer Learning with Probes
+
+```python
+from avex.models.probes import build_probe_from_config
+from avex.configs import ProbeConfig
+
+# Load backbone for feature extraction
+base = load_model("esp_aves2_sl_beats_all", return_features_only=True, device="cpu")
+
+# Define a probe head for your task
+probe_config = ProbeConfig(
+    probe_type="linear",
+    target_layers=["last_layer"],
+    aggregation="mean",
+    freeze_backbone=True,
+    online_training=True,
+)
+
+probe = build_probe_from_config(
+    probe_config=probe_config,
+    base_model=base,
+    num_classes=10,  # Your number of classes
+    device="cpu",
+)
+```
+
+## Documentation
+
+**Full documentation**: [docs/index.md](docs/index.md)
+
+### Core Documentation
+
+- **[API Reference](docs/api_reference.md)** - Complete API documentation for model loading, registry, and management functions
+- **[Architecture](docs/api_architecture.md)** - Framework architecture, core components, and plugin system
+- **[Supported Models](docs/supported_models.md)** - List of supported models and their configurations
+- **[Configuration](docs/configuration.md)** - ModelSpec parameters, audio requirements, and configuration options
+
+### Usage Guides
+
+- **[Training and Evaluation](docs/training_evaluation.md)** - Guide to training and evaluating models
+- **[Embedding Extraction](docs/embedding_extraction.md)** - Working with feature representations and embeddings
+- **[Examples](docs/examples.md)** - Comprehensive examples and use cases
+
+### Advanced Topics
+
+- **[Probe System](docs/probe_system.md)** - Understanding and using probes for transfer learning
+- **[API Probes](docs/api_probes.md)** - API reference for probe-related functionality
+- **[Custom Model Registration](docs/custom_model_registration.md)** - Guide on registering custom model classes and loading pre-trained models
+
+**Examples**: See the [`examples/`](examples/) directory:
+
+- `00_quick_start.py` - Basic model loading
+- `01_basic_model_loading.py` - Loading models with different configurations
+- `02_checkpoint_loading.py` - Working with checkpoints
+- `03_custom_model_registration.py` - Custom model registration
+- `04_training_and_evaluation.py` - Training and evaluation examples
+- `05_embedding_extraction.py` - Feature extraction
+- `06_classifier_head_loading.py` - Classifier head behavior
+
+## Supported Models
+
+The framework supports the following audio representation learning models:
+
+- **EfficientNet** - EfficientNet-based models for audio classification
+- **BEATs** - BEATs transformer models for audio representation learning
+- **EAT** - Efficient Audio Transformer models
+- **AVES** - AVES model for bioacoustics
+- **BirdMAE** - BirdMAE masked autoencoder for bioacoustic representation learning
+- **ATST** - Audio Spectrogram Transformer
+- **ResNet** - ResNet models (ResNet18, ResNet50, ResNet152)
+- **CLIP** - Contrastive Language-Audio Pretraining models
+- **BirdNet** - BirdNet models for bioacoustic classification
+- **Perch** - Perch models for bioacoustics
+- **SurfPerch** - SurfPerch models
+
+See [Supported Models](docs/supported_models.md) for detailed information and configuration examples.
+
+## Supported Probes
+
+The framework provides flexible probe heads for transfer learning:
+
+- **Linear** - Simple linear classifier (fastest, most memory-efficient)
+- **MLP** - Multi-layer perceptron with configurable hidden layers
+- **LSTM** - Long Short-Term Memory network for sequence modeling
+- **Attention** - Self-attention mechanism for sequence modeling
+- **Transformer** - Full transformer encoder architecture
+
+Probes can be trained:
+- **Online**: End-to-end with the backbone (raw audio input)
+- **Offline**: On pre-computed embeddings
+
+See [Probe System](docs/probe_system.md) and [API Probes](docs/api_probes.md) for detailed documentation.
+
+## Citing
+
+If you use this framework in your research, please cite:
+
+```bibtex
+@article{miron2025matters,
+  title={What Matters for Bioacoustic Encoding},
+  author={Miron, Marius and Robinson, David and Alizadeh, Milad and Gilsenan-McMahon, Ellen and Narula, Gagan and Pietquin, Olivier and Geist, Matthieu and Chemla, Emmanuel and Cusimano, Maddie and Effenberger, Felix and others},
+  journal={arXiv preprint arXiv:2508.11845},
+  year={2025}
+}
+```
+
+## Contributing
+
+We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for:
+
+- Development setup
+- Running tests
+- Code style guidelines
+- Adding new functionality
+- Pull request process
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Acknowledgments
+
+- Built on top of PyTorch
+- Integrates with various pre-trained audio models

avex-0.5.0a1/README.md

@@ -0,0 +1,203 @@
+# avex - Animal Vocalization Encoder Library
+
+![CI status](https://github.com/earthspecies/avex/actions/workflows/pythonapp.yml/badge.svg?branch=main)
+![Pre-commit status](https://github.com/earthspecies/avex/actions/workflows/pre-commit.yml/badge.svg?branch=main)
+
+An API for model loading and inference, and a Python-based system for training and evaluating bioacoustics representation learning models.
+
+## Description
+
+The Animal Vocalization Encoder library avex provides a unified interface for working with pre-trained bioacoustics representation learning models, with support for:
+
+- **Model Loading**: Load pre-trained models with checkpoints and class mappings
+- **Embedding Extraction**: Extract features from audio for downstream tasks
+- **Probe System**: Flexible probe heads (linear, MLP, LSTM, attention, transformer) for transfer learning
+- **Training & Evaluation**: Scripts for supervised learning experiments
+- **Plugin Architecture**: Register and use custom models seamlessly
+
+## Installation
+
+### Prerequisites
+
+- Python 3.10, 3.11, or 3.12
+
+### Install with pip
+
+```bash
+pip install avex
+```
+
+### Install with uv
+
+```bash
+uv add avex
+```
+
+For development installation with training/evaluation tools, see the [Contributing guide](CONTRIBUTING.md).
+
+## Quick Start
+
+```python
+import torch
+import librosa
+from avex import load_model, list_models
+
+# List available models
+print(list_models().keys())
+
+# Load a pre-trained model
+model = load_model("esp_aves2_sl_beats_all", device="cpu")
+
+# Load and preprocess audio (BEATs expects 16kHz)
+audio, sr = librosa.load("your_audio.wav", sr=16000)
+audio_tensor = torch.tensor(audio).unsqueeze(0)  # Shape: (1, num_samples)
+
+# Run inference
+with torch.no_grad():
+    logits = model(audio_tensor)
+    predicted_class = logits.argmax(dim=-1).item()
+
+# Get human-readable label
+if model.label_mapping:
+    label = model.label_mapping.get(str(predicted_class), predicted_class)
+    print(f"Predicted: {label}")
+```
+
+### Embedding Extraction
+
+```python
+# Load for embedding extraction (no classifier head)
+model = load_model("esp_aves2_sl_beats_all", return_features_only=True, device="cpu")
+
+with torch.no_grad():
+    embeddings = model(audio_tensor)
+    # Shape: (batch, time_steps, 768) for BEATs
+
+# Pool to get fixed-size embedding
+embedding = embeddings.mean(dim=1)  # Shape: (batch, 768)
+```
+
+### Transfer Learning with Probes
+
+```python
+from avex.models.probes import build_probe_from_config
+from avex.configs import ProbeConfig
+
+# Load backbone for feature extraction
+base = load_model("esp_aves2_sl_beats_all", return_features_only=True, device="cpu")
+
+# Define a probe head for your task
+probe_config = ProbeConfig(
+    probe_type="linear",
+    target_layers=["last_layer"],
+    aggregation="mean",
+    freeze_backbone=True,
+    online_training=True,
+)
+
+probe = build_probe_from_config(
+    probe_config=probe_config,
+    base_model=base,
+    num_classes=10,  # Your number of classes
+    device="cpu",
+)
+```
+
+## Documentation
+
+**Full documentation**: [docs/index.md](docs/index.md)
+
+### Core Documentation
+
+- **[API Reference](docs/api_reference.md)** - Complete API documentation for model loading, registry, and management functions
+- **[Architecture](docs/api_architecture.md)** - Framework architecture, core components, and plugin system
+- **[Supported Models](docs/supported_models.md)** - List of supported models and their configurations
+- **[Configuration](docs/configuration.md)** - ModelSpec parameters, audio requirements, and configuration options
+
+### Usage Guides
+
+- **[Training and Evaluation](docs/training_evaluation.md)** - Guide to training and evaluating models
+- **[Embedding Extraction](docs/embedding_extraction.md)** - Working with feature representations and embeddings
+- **[Examples](docs/examples.md)** - Comprehensive examples and use cases
+
+### Advanced Topics
+
+- **[Probe System](docs/probe_system.md)** - Understanding and using probes for transfer learning
+- **[API Probes](docs/api_probes.md)** - API reference for probe-related functionality
+- **[Custom Model Registration](docs/custom_model_registration.md)** - Guide on registering custom model classes and loading pre-trained models
+
+**Examples**: See the [`examples/`](examples/) directory:
+
+- `00_quick_start.py` - Basic model loading
+- `01_basic_model_loading.py` - Loading models with different configurations
+- `02_checkpoint_loading.py` - Working with checkpoints
+- `03_custom_model_registration.py` - Custom model registration
+- `04_training_and_evaluation.py` - Training and evaluation examples
+- `05_embedding_extraction.py` - Feature extraction
+- `06_classifier_head_loading.py` - Classifier head behavior
+
+## Supported Models
+
+The framework supports the following audio representation learning models:
+
+- **EfficientNet** - EfficientNet-based models for audio classification
+- **BEATs** - BEATs transformer models for audio representation learning
+- **EAT** - Efficient Audio Transformer models
+- **AVES** - AVES model for bioacoustics
+- **BirdMAE** - BirdMAE masked autoencoder for bioacoustic representation learning
+- **ATST** - Audio Spectrogram Transformer
+- **ResNet** - ResNet models (ResNet18, ResNet50, ResNet152)
+- **CLIP** - Contrastive Language-Audio Pretraining models
+- **BirdNet** - BirdNet models for bioacoustic classification
+- **Perch** - Perch models for bioacoustics
+- **SurfPerch** - SurfPerch models
+
+See [Supported Models](docs/supported_models.md) for detailed information and configuration examples.
+
+## Supported Probes
+
+The framework provides flexible probe heads for transfer learning:
+
+- **Linear** - Simple linear classifier (fastest, most memory-efficient)
+- **MLP** - Multi-layer perceptron with configurable hidden layers
+- **LSTM** - Long Short-Term Memory network for sequence modeling
+- **Attention** - Self-attention mechanism for sequence modeling
+- **Transformer** - Full transformer encoder architecture
+
+Probes can be trained:
+- **Online**: End-to-end with the backbone (raw audio input)
+- **Offline**: On pre-computed embeddings
+
+See [Probe System](docs/probe_system.md) and [API Probes](docs/api_probes.md) for detailed documentation.
+
+## Citing
+
+If you use this framework in your research, please cite:
+
+```bibtex
+@article{miron2025matters,
+  title={What Matters for Bioacoustic Encoding},
+  author={Miron, Marius and Robinson, David and Alizadeh, Milad and Gilsenan-McMahon, Ellen and Narula, Gagan and Pietquin, Olivier and Geist, Matthieu and Chemla, Emmanuel and Cusimano, Maddie and Effenberger, Felix and others},
+  journal={arXiv preprint arXiv:2508.11845},
+  year={2025}
+}
+```
+
+## Contributing
+
+We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for:
+
+- Development setup
+- Running tests
+- Code style guidelines
+- Adding new functionality
+- Pull request process
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Acknowledgments
+
+- Built on top of PyTorch
+- Integrates with various pre-trained audio models

avex-0.5.0a1/avex/__init__.py

@@ -0,0 +1,51 @@
+"""
+Representation Learning Framework
+
+A comprehensive Python-based system for training, evaluating, and analyzing
+audio representation learning models with support for both supervised and
+self-supervised learning paradigms.
+"""
+
+from importlib.metadata import version
+
+from .models.utils.factory import (
+    build_model,
+    build_model_from_spec,
+)
+from .models.utils.load import load_label_mapping, load_model
+from .models.utils.registry import (
+    describe_model,
+    get_checkpoint_path,
+    get_model_class,
+    get_model_spec,
+    list_model_classes,
+    list_model_layers,
+    list_models,
+    register_model,
+    register_model_class,
+)
+
+__version__ = version("avex")
+
+
+__all__ = [
+    # Model loading
+    "load_model",
+    # Registry management
+    "register_model",
+    "get_model_spec",
+    "list_models",
+    "describe_model",
+    "list_model_layers",
+    # Model class management
+    "register_model_class",
+    "get_model_class",
+    "list_model_classes",
+    # Model factory
+    "build_model",
+    "build_model_from_spec",
+    # Checkpoint management
+    "get_checkpoint_path",
+    # Label mapping management
+    "load_label_mapping",
+]

avex-0.5.0a1/avex/api/__init__.py

@@ -0,0 +1 @@
+"""API module for representation learning."""

avex-0.5.0a1/avex/api/configs/official_models/BEATs_iter3_plus_AS2M.yml

@@ -0,0 +1,17 @@
+---
+# BEATs iter3+AS2M SSL pretrained backbone
+# Self-supervised learning checkpoint without fine-tuning
+# Weights from HuggingFace: https://huggingface.co/lpepino/beats_ckpts
+checkpoint_path: hf://lpepino/beats_ckpts/BEATs_iter3_plus_AS2M.pt
+
+model_spec:
+  name: beats
+  pretrained: true
+  fine_tuned: false
+  device: cuda
+  audio_config:
+    sample_rate: 16000
+    representation: raw
+    normalize: false
+    target_length_seconds: 10
+    window_selection: random

avex-0.5.0a1/avex/api/configs/official_models/BEATs_iter3_plus_AS2M_finetuned_on_AS2M_cpt2.yml

@@ -0,0 +1,17 @@
+---
+# BEATs iter3+AS2M fine-tuned backbone
+# Fine-tuned on AudioSet 2M classification
+# Weights from HuggingFace: https://huggingface.co/THUdyh/Ola_speech_encoders
+checkpoint_path: hf://THUdyh/Ola_speech_encoders/BEATs_iter3_plus_AS2M_finetuned_on_AS2M_cpt2.pt
+
+model_spec:
+  name: beats
+  pretrained: true
+  fine_tuned: true
+  device: cuda
+  audio_config:
+    sample_rate: 16000
+    representation: raw
+    normalize: false
+    target_length_seconds: 10
+    window_selection: random

avex-0.5.0a1/avex/api/configs/official_models/__init__.py

@@ -0,0 +1 @@
+"""Official model configurations."""

avex-0.5.0a1/avex/api/configs/official_models/esp_aves2_eat_all.yml

@@ -0,0 +1,17 @@
+---
+# ESP-AVES2: EAT trained on all (AudioSet + bio) data.
+# Weights on Hugging Face Hub (safetensors). Load via hf:// URIs.
+checkpoint_path: hf://EarthSpeciesProject/esp-aves2-eat-all/esp-aves2-eat-all.safetensors
+
+model_spec:
+  name: eat_hf
+  pretrained: false
+  device: cuda
+  eat_norm_mean: -5.553
+  eat_norm_std: 4.606
+  audio_config:
+    sample_rate: 16000
+    representation: raw
+    normalize: false
+    target_length_seconds: 10
+    window_selection: random

avex-0.5.0a1/avex/api/configs/official_models/esp_aves2_eat_bio.yml

@@ -0,0 +1,17 @@
+---
+# ESP-AVES2: EAT trained on bio data.
+# Weights on Hugging Face Hub (safetensors). Load via hf:// URIs.
+checkpoint_path: hf://EarthSpeciesProject/esp-aves2-eat-bio/esp-aves2-eat-bio.safetensors
+
+model_spec:
+  name: eat_hf
+  pretrained: false
+  device: cuda
+  eat_norm_mean: -5.553
+  eat_norm_std: 4.606
+  audio_config:
+    sample_rate: 16000
+    representation: raw
+    normalize: false
+    target_length_seconds: 10
+    window_selection: random

avex-0.5.0a1/avex/api/configs/official_models/esp_aves2_effnetb0_all.yml

@@ -0,0 +1,22 @@
+---
+# ESP-AVES2: EfficientNet B0 trained on all (AudioSet + bio) data.
+# Weights on Hugging Face Hub (safetensors). Load via hf:// URIs.
+checkpoint_path: hf://EarthSpeciesProject/esp-aves2-effnetb0-all/esp-aves2-effnetb0-all.safetensors
+class_mapping_path: hf://EarthSpeciesProject/esp-aves2-effnetb0-all/label_map.json
+
+model_spec:
+  name: efficientnet
+  pretrained: false
+  device: cuda
+  efficientnet_variant: b0
+  audio_config:
+    sample_rate: 16000
+    n_fft: 800
+    hop_length: 160
+    win_length: 800
+    window: hann
+    n_mels: 128
+    representation: mel_spectrogram
+    normalize: true
+    target_length_seconds: 10
+    window_selection: random

avex-0.5.0a1/avex/api/configs/official_models/esp_aves2_effnetb0_audioset.yml

@@ -0,0 +1,21 @@
+---
+# ESP-AVES2: EfficientNet B0 trained on AudioSet.
+# Weights on Hugging Face Hub (safetensors). Load via hf:// URIs.
+checkpoint_path: hf://EarthSpeciesProject/esp-aves2-effnetb0-audioset/esp-aves2-effnetb0-audioset.safetensors
+
+model_spec:
+  name: efficientnet
+  pretrained: false
+  device: cuda
+  efficientnet_variant: b0
+  audio_config:
+    sample_rate: 16000
+    n_fft: 800
+    hop_length: 160
+    win_length: 800
+    window: hann
+    n_mels: 128
+    representation: mel_spectrogram
+    normalize: true
+    target_length_seconds: 10
+    window_selection: random

avex-0.5.0a1/avex/api/configs/official_models/esp_aves2_effnetb0_bio.yml

@@ -0,0 +1,22 @@
+---
+# ESP-AVES2: EfficientNet B0 trained on bio data.
+# Weights on Hugging Face Hub (safetensors). Load via hf:// URIs.
+checkpoint_path: hf://EarthSpeciesProject/esp-aves2-effnetb0-bio/esp-aves2-effnetb0-bio.safetensors
+class_mapping_path: hf://EarthSpeciesProject/esp-aves2-effnetb0-bio/label_map.json
+
+model_spec:
+  name: efficientnet
+  pretrained: false
+  device: cuda
+  efficientnet_variant: b0
+  audio_config:
+    sample_rate: 16000
+    n_fft: 800
+    hop_length: 160
+    win_length: 800
+    window: hann
+    n_mels: 128
+    representation: mel_spectrogram
+    normalize: true
+    target_length_seconds: 10
+    window_selection: random

avex-0.5.0a1/avex/api/configs/official_models/esp_aves2_naturelm_audio_v1_beats.yml

@@ -0,0 +1,16 @@
+---
+# ESP-AVES2: BEATs with NatureLM (audio v1).
+# Weights on Hugging Face Hub (safetensors). Load via hf:// URIs.
+checkpoint_path: hf://EarthSpeciesProject/esp-aves2-naturelm-audio-v1-beats/esp-aves2-naturelm-audio-v1-beats.safetensors
+
+model_spec:
+  name: beats
+  pretrained: false
+  device: cuda
+  use_naturelm: true
+  audio_config:
+    sample_rate: 16000
+    representation: raw
+    normalize: false
+    target_length_seconds: 10
+    window_selection: random