Hugging Face's logo

nvidia
/
diar_sortformer_4spk-v1

Automatic Speech Recognition
NeMo
Safetensors
PyTorch
sortformer
speaker-diarization
speaker-recognition
speech
audio
Transformer
FastConformer
Conformer
NEST
NeMo
Eval Results (legacy)
Model card Files
xet
 Community
13
taejinp commited on
Commit
ebfd651
·
verified ·
1 Parent(s): ea494c8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -209,7 +209,7 @@ The model can be trained using this [example script](https://github.com/NVIDIA/N
209
 
210
  To evaluate Sortformer diarizer and save diarization results in RTTM format, use the inference [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py):
211
  ```bash
212
- python [NEMO_GIT_FOLDER]/examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py
213
  model_path="/path/to/diar_sortformer_4spk-v1.nemo" \
214
  manifest_filepath="/path/to/multispeaker_manifest_with_reference_rttms.json" \
215
  collar=COLLAR \
@@ -218,7 +218,7 @@ python [NEMO_GIT_FOLDER]/examples/speaker_tasks/diarization/neural_diarizer/e2e_
218
 
219
  You can provide the post-processing YAML configs from [`post_processing` folder](https://github.com/NVIDIA/NeMo/tree/main/examples/speaker_tasks/diarization/conf/post_processing) to reproduce the optimized post-processing algorithm for each development dataset:
220
  ```bash
221
- python [NEMO_GIT_FOLDER]/examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py \
222
  model_path="/path/to/diar_sortformer_4spk-v1.nemo" \
223
  manifest_filepath="/path/to/multispeaker_manifest_with_reference_rttms.json" \
224
  collar=COLLAR \
 
209
 
210
  To evaluate Sortformer diarizer and save diarization results in RTTM format, use the inference [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py):
211
  ```bash
212
+ python ${NEMO_GIT_FOLDER}/examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py
213
  model_path="/path/to/diar_sortformer_4spk-v1.nemo" \
214
  manifest_filepath="/path/to/multispeaker_manifest_with_reference_rttms.json" \
215
  collar=COLLAR \
 
218
 
219
  You can provide the post-processing YAML configs from [`post_processing` folder](https://github.com/NVIDIA/NeMo/tree/main/examples/speaker_tasks/diarization/conf/post_processing) to reproduce the optimized post-processing algorithm for each development dataset:
220
  ```bash
221
+ python ${NEMO_GIT_FOLDER}/examples/speaker_tasks/diarization/neural_diarizer/e2e_diarize_speech.py \
222
  model_path="/path/to/diar_sortformer_4spk-v1.nemo" \
223
  manifest_filepath="/path/to/multispeaker_manifest_with_reference_rttms.json" \
224
  collar=COLLAR \