NeMo
NeMo copied to clipboard
NVIDIA
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
# What does this PR do ? Adding support for models trained with full context for cache-aware streaming. **Collection**: ASR # Changelog Adding support for models trained with full context...
Signed-off-by: Ante Jukić # What does this PR do ? This PR adds pre-trained models for Croatian. **Collection**: [ASR] # Changelog - updated `PretrainedModelInfo` and docs - minor (cosmetic) modifications...
Signed-off-by: Iztok Lebar Bajec # What does this PR do ? While waiting for #3819 to be finished, upgrade of current punctuation capitalization model with support for lowercasing, uppercasing, and...
[Speech Data Explorer] An option to explicitly specify the base dir for manifests with relative paths **Collection**: Tools # Changelog - Use `args.audio_base_path` instead of `args.manifest` - If `args.audio_base_path` is...
Signed-off-by: Paarth Neekhara # What does this PR do ? Fixes a bug where sample rate was being ignored in VocoderDataset when loading just the audio and audio lengths and...
Hi! I am trying `nvidia/stt_en_conformer_transducer_xlarge` for my ASR system and the performance is impressive. I noticed that there is an option in transcribe function that can support lm_score in output....
Signed-off-by: sarthmit # What does this PR do ? Fixes the seed for everything (training/initialization/etc.) during training of nlp machine translation systems to aid reproducibility. **Collection**: examples/nlp/machine_translation # Changelog -...
Fixes installation issues in a normal python virtual environment when conda is also present on the same system. Also remove double negation. Signed-off-by: Anand Joseph # What does this PR...
**Unable to import ASR model from Nemo.Collections ** **import nemo.collections.asr as nemo_asr** **Expected behavior** A clear and concise description of what you expected to happen. **Environment overview (please complete the...
**Describe the bug** Trying to run `megatron_nmt_training.py`, with `conf/aayn_base_megatron.yml` initialization crashes with the following trace: ```python Traceback (most recent call last): File "examples/nlp/machine_translation/megatron_nmt_training.py", line 95, in main() File "/workspace/nemo/nemo/core/config/hydra_runner.py", line...