SLAM-LLM
SLAM-LLM copied to clipboard
X-LANCE
Speech, Language, Audio, Music Processing with Large Language Model
Anyone has tried to use the SLAM toolkit to run Spoken Language Understanding? Or simply , some classification tasks by leveraging the ASR recipe
[decode_whisper_large_linear_vicuna_7b.txt](https://github.com/user-attachments/files/19158669/decode_whisper_large_linear_vicuna_7b.txt) Hello everybody, I am attempting to perform ASR using Vicuna-7B and Whisper Large V3 on a system with two NVIDIA GPUs (24GB each) connected via NVLink. However, I consistently...
I'm not sure if it's a problem with my instruction design. ```text dataset_config: # we put prompt here, because the hydra override in shell script only support a small subset...
### 🚀 The feature, motivation and pitch Could you provide preprocess and metric computing code for mala-asr？ ### Alternatives _No response_ ### Additional context _No response_
Discrepancy in Metric Calculation (WER, U-WER, B-WER, Recall) onMALA-ASR with Slidespeech Test Set
I ran inference using the Slidespeech test set on MALA-ASR and generated thedecode_test beam4_pred and decode test beam4 gt files. However, the metrics(WER, U-WER, B-WER, Recall) I calculated from these...
upload metric computing code for WER,B-WER,U-WER and Recall.
Hello can u help me? I have a problem with some errors first there was a problem with self tokenization of example_ids : "pad_token_id or eos_token_id is None. And now...
### System Info The versions are as in reqs.txt ### Information - [X] The official example scripts - [ ] My own modified scripts ### 🐛 Describe the bug getting...
### System Info what does split mean hear,as no difference between train or others? self.data_list = [] if split == "train": with open(dataset_config.train_data_path, encoding='utf-8') as fin: for line in fin:...
