Diar Sortformer 4spk V1

🚀 Sortformer Diarizer 4spk v1

Sortformer Diarizer 4spk v1 is a novel end - to - end neural model for speaker diarization. It resolves the permutation problem in diarization and is trained with unconventional objectives compared to existing models.

|

Sortformer[1] is a novel end-to-end neural model for speaker diarization, trained with unconventional objectives compared to existing end-to-end diarization models.

Sortformer resolves the permutation problem in diarization following the arrival-time order of the speech segments from each speaker.

✨ Features

• Novel Architecture: Based on FastConformer - Transformer, it uses an L - size (18 layers) NeMo Encoder for Speech Tasks (NEST)[2] and an 18 - layer Transformer encoder.
• End - to - End: Capable of performing speaker diarization in an end - to - end manner.
• Multiple Datasets Support: Trained on a variety of datasets including Fisher English, Librispeech, etc.

📦 Installation

To train, fine - tune or perform diarization with Sortformer, you will need to install NVIDIA NeMo[5]. We recommend you install it after you've installed Cython and the latest PyTorch version.

apt-get update && apt-get install -y libsndfile1 ffmpeg
pip install Cython packaging
pip install git+https://github.com/NVIDIA/NeMo.git@main#egg=nemo_toolkit[asr]

💻 Usage Examples

Loading the Model

from nemo.collections.asr.models import SortformerEncLabelModel

# load model from Hugging Face model card directly (You need a Hugging Face token)
diar_model = SortformerEncLabelModel.from_pretrained("nvidia/diar_sortformer_4spk-v1")

# If you have a downloaded model in "/path/to/diar_sortformer_4spk-v1.nemo", load model from a downloaded file
diar_model = SortformerEncLabelModel.restore_from(restore_path="/path/to/diar_sortformer_4spk-v1.nemo", map_location='cuda', strict=False)

# switch to inference mode
diar_model.eval()

Input Format

Input to Sortformer can be an individual audio file:

audio_input="/path/to/multispeaker_audio1.wav"

or a list of paths to audio files:

audio_input=["/path/to/multispeaker_audio1.wav", "/path/to/multispeaker_audio2.wav"]

or a jsonl manifest file:

audio_input="/path/to/multispeaker_manifest.json"

where each line is a dictionary containing the following fields:

# Example of a line in `multispeaker_manifest.json`
{
    "audio_filepath": "/path/to/multispeaker_audio1.wav",  # path to the input audio file 
    "offset": 0, # offset (start) time of the input audio
    "duration": 600,  # duration of the audio, can be set to `null` if using NeMo main branch
}
{
    "audio_filepath": "/path/to/multispeaker_audio2.wav",  
    "offset": 900,
    "duration": 580,  
}

Getting Diarization Results

To perform speaker diarization and get a list of speaker - marked speech segments in the format 'begin_seconds, end_seconds, speaker_index', simply use:

predicted_segments = diar_model.diarize(audio=audio_input, batch_size=1)

To obtain tensors of speaker activity probabilities, use:

predicted_segments, predicted_probs = diar_model.diarize(audio=audio_input, batch_size=1, include_tensor_outputs=True)

📚 Documentation

Input

This model accepts single - channel (mono) audio sampled at 16,000 Hz.

• The actual input tensor is a Ns x 1 matrix for each audio clip, where Ns is the number of samples in the time - series signal.
• For instance, a 10 - second audio clip sampled at 16,000 Hz (mono - channel WAV file) will form a 160,000 x 1 matrix.

Output

The output of the model is a T x S matrix, where:

• S is the maximum number of speakers (in this model, S = 4).
• T is the total number of frames, including zero - padding. Each frame corresponds to a segment of 0.08 seconds of audio.
• Each element of the T x S matrix represents the speaker activity probability in the [0, 1] range. For example, a matrix element a(150, 2) = 0.95 indicates a 95% probability of activity for the second speaker during the time range [12.00, 12.08] seconds.

Train and evaluate Sortformer diarizer using NeMo

Training

Sortformer diarizer models are trained on 8 nodes of 8×NVIDIA Tesla V100 GPUs. We use 90 - second long training samples and a batch size of 4. The model can be trained using this example script and base config.

Evaluation

To evaluate Sortformer diarizer and save diarization results in RTTM format, use the inference example script:

python ${NEMO_GIT_FOLDER}/examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py 
 model_path="/path/to/diar_sortformer_4spk-v1.nemo" \
 manifest_filepath="/path/to/multispeaker_manifest_with_reference_rttms.json" \
 collar=COLLAR \
 out_rttm_dir="/path/to/output_rttms"

You can provide the post - processing YAML configs from post_processing folder to reproduce the optimized post - processing algorithm for each development dataset:

python ${NEMO_GIT_FOLDER}/examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py \
 model_path="/path/to/diar_sortformer_4spk-v1.nemo" \
 manifest_filepath="/path/to/multispeaker_manifest_with_reference_rttms.json" \
 collar=COLLAR \
 bypass_postprocessing=False \
 postprocessing_yaml="/path/to/postprocessing_config.yaml" \
 out_rttm_dir="/path/to/output_rttms"

Technical Limitations

• The model operates in a non - streaming mode (offline mode).
• It can detect a maximum of 4 speakers; performance degrades on recordings with 5 and more speakers.
• The maximum duration of a test recording depends on available GPU memory. For an RTX A6000 48GB model, the limit is around 12 minutes.
• The model was trained on publicly available speech datasets, primarily in English. As a result:
  • Performance may degrade on non - English speech.
  • Performance may also degrade on out - of - domain data, such as recordings in noisy conditions.

Datasets

Sortformer was trained on a combination of 2030 hours of real conversations and 5150 hours or simulated audio mixtures generated by NeMo speech data simulator[6]. All the datasets listed above are based on the same labeling method via RTTM format. A subset of RTTM files used for model training are processed for the speaker diarization model training purposes. Data collection methods vary across individual datasets. For example, the above datasets include phone calls, interviews, web videos, and audiobook recordings. Please refer to the Linguistic Data Consortium (LDC) website or dataset webpage for detailed data collection methods.

Training Datasets (Real conversations)

• Fisher English (LDC)
• 2004 - 2010 NIST Speaker Recognition Evaluation (LDC)
• Librispeech
• AMI Meeting Corpus
• VoxConverse - v0.3
• ICSI
• AISHELL - 4
• Third DIHARD Challenge Development (LDC)
• 2000 NIST Speaker Recognition Evaluation, split1 (LDC)

Training Datasets (Used to simulate audio mixtures)

• 2004 - 2010 NIST Speaker Recognition Evaluation (LDC)
• Librispeech

Performance

Evaluation dataset specifications

Diarization Error Rate (DER)

• All evaluations include overlapping speech.
• Bolded and italicized numbers represent the best - performing Sortformer evaluations.
• Post - Processing (PP) is optimized on two different held - out dataset splits.
  • YAML file for DH3 - dev Optimized Post - Processing
  • YAML file for CallHome - part1 Optimized Post - Processing

Real Time Factor (RTFx)

All tests were measured on RTX A6000 48GB with batch size of 1. Post - processing is not included in RTFx calculations.

🔧 Technical Details

Sortformer consists of an L - size (18 layers) NeMo Encoder for Speech Tasks (NEST)[2] which is based on Fast - Conformer[3] encoder. Following that, an 18 - layer Transformer[4] encoder with hidden size of 192, and two feedforward layers with 4 sigmoid outputs for each frame input at the top layer. More information can be found in the Sortformer paper[1].

📄 License

This model is licensed under the CC - BY - NC - 4.0 license.