Add wav2vec2 model for Spark (#131)

* Add wav2vec2 model for Spark.

* fix indexing

* fix mel

* fix indices

---------

Co-authored-by: Prince Canuma <[email protected]>

Author: lucasnewman

mlx_audio/codec/models/vocos/mel.py

@@ -41,8 +41,11 @@ def mel_to_hz(mels, mel_scale="htk"):
         min_log_hz = 1000.0
         min_log_mel = (min_log_hz - f_min) / f_sp
         logstep = math.log(6.4) / 27.0
-        log_t = mels >= min_log_mel
-        freqs[log_t] = min_log_hz * mx.exp(logstep * (mels[log_t] - min_log_mel))
+        freqs = mx.where(
+            mels >= min_log_mel,
+            min_log_hz * mx.exp(logstep * (mels - min_log_mel)),
+            freqs,
+        )
         return freqs
 
     f_max = f_max or sample_rate / 2
@@ -103,6 +106,9 @@ def _pad(x, padding, pad_mode="constant"):
         else:
             raise ValueError(f"Invalid pad_mode {pad_mode}")
 
+    if window.shape[0] < nfft:
+        window = mx.pad(window, (0, nfft - window.shape[0]))
+
     padding = nperseg // 2
     x = _pad(x, padding, pad_mode)