Initial commit: FunASR Speech Recognition Toolkit

Add complete FunASR codebase including models, runtime, and documentation.
2026-07-09 22:38:58 +08:00
commit 6116b1f3c6
3683 changed files with 990984 additions and 0 deletions
@@ -0,0 +1,45 @@
+# 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."]