Some weights of the model checkpoint at jonatasgrosman/wav2vec2-large-xlsr-53-english were not used when initializing Wav2Vec2Model: ['lm_head.weight', 'lm_head.bias']

[saba99]

Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from 'data/audio/German4.wav':
Metadata:
encoder : Lavf58.29.100
Duration: 00:00:06.84, bitrate: 256 kb/s
Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (pcm_s16le (native) -> pcm_s16le (native))
Press [q] to stop, [?] for help
-async is forwarded to lavfi similarly to -af aresample=async=1:min_hard_comp=0.100000:first_pts=0.
Output #0, wav, to 'tmp/codeformer_sr_english@M030_front_neutral_level1_001@male_face/codeformer_sr_english@M030_front_neutral_level1_001@male_face_16K.wav':
Metadata:
ISFT : Lavf58.76.100
Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s
Metadata:
encoder : Lavc58.134.100 pcm_s16le
size= 214kB time=00:00:06.78 bitrate= 258.2kbits/s speed= 192x
video:0kB audio:214kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.035636%
Some weights of the model checkpoint at jonatasgrosman/wav2vec2-large-xlsr-53-english were not used when initializing Wav2Vec2Model: ['lm_head.weight', 'lm_head.bias']

• This IS expected if you are initializing Wav2Vec2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
• This IS NOT expected if you are initializing Wav2Vec2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  2024-02-25 18:04:43.131416: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/lib/python3.10/dist-packages/cv2/../../lib64:/usr/lib64-nvidia
  /usr/local/lib/python3.10/dist-packages/torch/nn/functional.py:4193: UserWarning: Default grid_sample and affine_grid behavior has changed to align_corners=False since 1.3.0. Please specify align_corners=True if the old behavior is desired. See the documentation of grid_sample for details.
  warnings.warn(

[us-Mike]

I met the same question。

[YifengMa9]

The warning message "Some weights ... Wav2Vec2Model: ['lm_head.weight', 'lm_head.bias']" is not an issue and does not indicate a program error. Apologies for any confusion caused by not removing this message.