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
Fix PCM16 and multichannel array input with NumPy CI
LauraGPT8a370f11e255
diff --cc .github/workflows/test-numpy-compatibility.ymlindex 370553668,370553668,370553668..bfeeff440--- a/.github/workflows/test-numpy-compatibility.yml+++ b/.github/workflows/test-numpy-compatibility.yml@@@@ -30,6 -30,6 -30,6 +30,8 @@@@ on- "tests/test_ct_transformer_streaming_empty_input.py"- "tests/test_pcm_input_format.py"- "tests/test_load_audio_bytes.py"+++ - "tests/test_load_audio_int16_array.py"+++ - "tests/test_load_audio_multichannel_arrays.py"- "funasr/frontends/**"- "funasr/models/normalize/utterance_mvn.py"- "tests/test_utterance_mvn.py"@@@@ -74,6 -74,6 -74,6 +76,8 @@@@- "tests/test_ct_transformer_streaming_empty_input.py"- "tests/test_pcm_input_format.py"- "tests/test_load_audio_bytes.py"+++ - "tests/test_load_audio_int16_array.py"+++ - "tests/test_load_audio_multichannel_arrays.py"- "funasr/frontends/**"- "funasr/models/normalize/utterance_mvn.py"- "tests/test_utterance_mvn.py"@@@@ -146,6 -146,6 -146,6 +150,8 @@@@ jobstests/test_realtime_ws_service.py \tests/test_realtime_ws_hf_overrides.py \tests/test_load_audio_bytes.py \+++ tests/test_load_audio_int16_array.py \+++ tests/test_load_audio_multichannel_arrays.py \tests/test_timestamp_tools.py \tests/test_punc_model_none.py \tests/test_paraformer_empty_token_batch.py \