Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
vad
游雁3891583cf117
diff --git a/examples/aishell/llm_asr_nar/conf/template.yaml b/examples/aishell/llm_asr_nar/conf/template.yamldeleted file mode 100644index d52963575..000000000--- a/examples/aishell/llm_asr_nar/conf/template.yaml+++ /dev/null@@ -1,93 +0,0 @@-# This is an example that demonstrates how to configure a model file.-# You can modify the configuration according to your own requirements.--# to print the register_table:-# from funasr.register import tables-# tables.print()--# network architecture-model: LLMASRNAR-model_conf:- lsm_weight: 0.1 # label smoothing option- length_normalized_loss: true--# encoder-encoder: Paraformer-encoder_conf:- hub: funasr- init_param_path: "iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"- freeze: false--llm: Vicuna-llm_conf:- hub: hf- init_param_path: "/nfs/maziyang.mzy/models/vicuna-7b-v1.5"- freeze: true--adaptor: Linear-adaptor_conf:- downsample_rate: 1- llm_dim: 4096- encoder_dim: 512--# frontend related-frontend: WavFrontend-frontend_conf:- fs: 16000- window: hamming- n_mels: 80- frame_length: 25- frame_shift: 10- lfr_m: 7- lfr_n: 6- cmvn_file: "/root/.cache/modelscope/hub/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/am.mvn"--specaug: SpecAugLFR-specaug_conf:- apply_time_warp: false- time_warp_window: 5- time_warp_mode: bicubic- apply_freq_mask: true- freq_mask_width_range:- - 0- - 30- lfr_rate: 6- num_freq_mask: 1- apply_time_mask: true- time_mask_width_range:- - 0- - 12- num_time_mask: 1--train_conf:- accum_grad: 1- grad_clip: 5- max_epoch: 150- keep_nbest_models: 10- log_interval: 10--optim: adamw-optim_conf:- lr: 0.0001- weight_decay: 0.000001-scheduler: warmuplr-scheduler_conf:- warmup_steps: 1500--dataset: AudioLLMDataset-dataset_conf:- index_ds: IndexDSJsonl- batch_sampler: RankFullLocalShuffleBatchSampler- batch_type: example # example or length- batch_size: 8 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;- max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,- buffer_size: 500- shuffle: True- num_workers: 4- preprocessor_text: TextPreprocessRemovePunctuation--tokenizer: HuggingfaceTokenizer-tokenizer_conf:- unk_symbol: <unk>- init_param_path: "/nfs/maziyang.mzy/models/vicuna-7b-v1.5"-