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)
Is it possible to add new tokens to the tokeniser of a pretrained model. say I want to fine tune on some new data, which contains few new tokens eg....
# What does this PR do ? Add a one line overview of what this PR aims to accomplish. **Collection**: [Note which collection this PR will affect] # Changelog -...
# What does this PR do ? Adds support for training GPT-3 with the [Apex implementation of the ZeRO optimizer](https://github.com/NVIDIA/apex/blob/master/apex/contrib/optimizers/distributed_fused_adam.py). **Collection**: NLP # Changelog - Add option for `distributed_fused_adam` optimizer...
# What does this PR do ? Move TTS tokenizers to collections.common.tokenizers so they can be used in cross-collections pipelines. For implementing ASR/ST model training which generates samples on-the-fly with...
Signed-off-by: Taejin Park # What does this PR do ? Add multiscale diarization decoder model module, and yaml files. Additionally, yaml files are also uploaded. - msdd_models.py Three classes are...
# What does this PR do ? Adds a multispeaker audio session simulator and corresponding documentation and tutorials. Collections: ASR, Tools # Changelog - Adds data simulator - Adds a...
Signed-off-by: Jocelyn Huang # What does this PR do ? Adds NGC model loading for the RAD-TTS Aligner. **Collection**: TTS # Changelog - Add newly published NGC checkpoint to list...
Signed-off-by: nithinraok # What does this PR do ? Add a one line overview of what this PR aims to accomplish. **Collection**: [Note which collection this PR will affect] #...
# What does this PR do ? To handle very large dataset, e.g. hundreds of gigabyte to terrabyte compressed raw data, we need multiple nodes to create sharding index and...
# What does this PR do ? implements prefix tuning for Megatron GPT models. **Collection**: `examples/nlp/languge_modeling` # Changelog - Add specific line by line info of high level changes in...