Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

936 B
Raw Blame
# 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: WhisperWarp
model_conf:
    lsm_weight: 0.1
    length_normalized_loss: true
    hub: funasr # openai



# only use for hub == funasr,
#  if hub == openai, dims is automaticall download
dims:
    n_mels: 128
    n_vocab: 51866
    n_audio_ctx: 1500
    n_audio_state: 1280
    n_audio_head: 20
    n_audio_layer: 32
    n_text_ctx: 448
    n_text_state: 1280
    n_text_head: 20
    n_text_layer: 32

# frontend related
frontend: WhisperFrontend
frontend_conf:
    fs: 16000
    n_mels: ${dims.n_mels}
    do_pad_trim: true

tokenizer: WhisperTokenizer
tokenizer_conf:
  language: null
  task: transcribe
  is_multilingual: true
  num_languages: 100

scope_map: [none, "model."]