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']

[Yazdi9]

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(

[developer-JingHSY]

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.

[gpfworld]

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.

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.

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.

Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'data/audio/acknowledgement_english.m4a':
Metadata:
major_brand : M4A
minor_version : 0
compatible_brands: M4A isommp42
creation_time : 2023-12-20 14:25:20
iTunSMPB : 00000000 00000840 00000000 00000000000C23C0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
Duration: 00:00:16.57, start: 0.000000, bitrate: 246 kb/s
Stream #0:0(und): Audio: aac (LC) (mp4a / 0x6134706D), 48000 Hz, mono, fltp, 244 kb/s (default)
Metadata:
creation_time : 2023-12-20 14:25:20
handler_name : Core Media Audio
-async is forwarded to lavfi similarly to -af aresample=async=1:min_hard_comp=0.100000:first_pts=0.
Output #0, wav, to 'tmp/acknowledgement_english@M030_front_neutral_level1_001@male_face/acknowledgement_english@M030_front_neutral_level1_001@male_face_16K.wav':
Metadata:
major_brand : M4A
minor_version : 0
compatible_brands: M4A isommp42
iTunSMPB : 00000000 00000840 00000000 00000000000C23C0 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
ISFT : Lavf57.25.100
Stream #0:0(und): Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s (default)
Metadata:
creation_time : 2023-12-20 14:25:20
handler_name : Core Media Audio
encoder : Lavc57.24.102 pcm_s16le
Stream mapping:
Stream #0:0 -> #0:0 (aac (native) -> pcm_s16le (native))
Press [q] to stop, [?] for help
size= 519kB time=00:00:16.61 bitrate= 256.0kbits/s speed=64.5x
video:0kB audio:519kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.014667%
Some weights of the model checkpoint at jonatasgrosman/wav2vec2-large-xlsr-53-english were not used when initializing Wav2Vec2Model: ['lm_head.bias', 'lm_head.weight']

• 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).
  Segmentation fault (core dumped)

I met the same question