Moonshine wrong output

[thewh1teagle]

https://github.com/k2-fsa/sherpa-onnx/releases/download/v1.10.30/sherpa-onnx-v1.10.30-osx-universal2-shared.tar.bz2
tar xf sherpa-onnx-v1.10.30-osx-universal2-shared.tar.bz2
./sherpa-onnx-v1.10.30-osx-universal2-shared/bin/sherpa-onnx-offline \
    --moonshine-preprocessor="sherpa-onnx-moonshine-tiny-en-int8/preprocess.onnx" \
    --moonshine-encoder="sherpa-onnx-moonshine-tiny-en-int8/encode.int8.onnx" \
    --moonshine-uncached-decoder="sherpa-onnx-moonshine-tiny-en-int8/uncached_decode.int8.onnx" \
    --moonshine-cached-decoder="sherpa-onnx-moonshine-tiny-en-int8/cached_decode.int8.onnx" \
    --tokens="sherpa-onnx-moonshine-tiny-en-int8/tokens.txt" \
    --num-threads=1 \
    audio.wav # https://www.youtube.com/watch?v=hjkIIWt4bUI English

Output:

./sherpa-onnx-v1.10.30-osx-universal2-shared/bin/sherpa-onnx-offline \
    --moonshine-preprocessor="sherpa-onnx-moonshine-tiny-en-int8/preprocess.onnx" \
    --moonshine-encoder="sherpa-onnx-moonshine-tiny-en-int8/encode.int8.onnx" \
    --moonshine-uncached-decoder="sherpa-onnx-moonshine-tiny-en-int8/uncached_decode.int8.onnx" \
    --moonshine-cached-decoder="sherpa-onnx-moonshine-tiny-en-int8/cached_decode.int8.onnx" \
    --tokens="sherpa-onnx-moonshine-tiny-en-int8/tokens.txt" \
    --num-threads=1 \
    audio.wav
/Users/runner/work/sherpa-onnx/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:375 ./sherpa-onnx-v1.10.30-osx-universal2-shared/bin/sherpa-onnx-offline --moonshine-preprocessor=sherpa-onnx-moonshine-tiny-en-int8/preprocess.onnx --moonshine-encoder=sherpa-onnx-moonshine-tiny-en-int8/encode.int8.onnx --moonshine-uncached-decoder=sherpa-onnx-moonshine-tiny-en-int8/uncached_decode.int8.onnx --moonshine-cached-decoder=sherpa-onnx-moonshine-tiny-en-int8/cached_decode.int8.onnx --tokens=sherpa-onnx-moonshine-tiny-en-int8/tokens.txt --num-threads=1 audio.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model=""), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="sherpa-onnx-moonshine-tiny-en-int8/preprocess.onnx", encoder="sherpa-onnx-moonshine-tiny-en-int8/encode.int8.onnx", uncached_decoder="sherpa-onnx-moonshine-tiny-en-int8/uncached_decode.int8.onnx", cached_decoder="sherpa-onnx-moonshine-tiny-en-int8/cached_decode.int8.onnx"), telespeech_ctc="", tokens="sherpa-onnx-moonshine-tiny-en-int8/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="")
Creating recognizer ...
Started
Done!

audio.wav
{"lang": "", "emotion": "", "event": "", "text": " and the other parts of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe are the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the universe, and the elements of the universe, and the elements of the universe, and the elements of the universe, and the universe, and the elements of the elements of the elements of the universe, and the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements of the elements", "timestamps": [], "tokens":[" and", " the", " other", " parts", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", " are", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " universe", ",", " and", " the", " universe", ",", " and", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " universe", ",", " and", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements", " of", " the", " elements"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 28.463 s
Real time factor (RTF): 28.463 / 127.516 = 0.223

Correct transcript: https://youtubetranscript.com/?v=hjkIIWt4bUI

[csukuangfj]

could you upload the test wav?

also, is there a reason to send such a long wav directly to a non-streaming model?

[thewh1teagle]

could you upload the test wav?

https://github.com/thewh1teagle/sherpa-rs/releases/download/v0.5.1/moonshaine-test.wav

also, is there a reason to send such a long wav directly to a non-streaming model?

I just do simple tests and it's just 2 minutes. I remember that you said that the model doesn't have inference size limitation like whisper?